Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to computer codes or formatting artifacts that are typically used for editing text

    oai_token-act-pair · gpt-3.5-turbo

    numeric data and statistics related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reneg
    -0.77
     frontline
    -0.76
     star
    -0.75
     spear
    -0.73
     brid
    -0.73
     covenant
    -0.72
     consulate
    -0.72
     revers
    -0.71
     doub
    -0.71
     honoured
    -0.69
    POSITIVE LOGITS
    --------------------------------------------------------
    1.64
    Advertisements
    1.53
    ________________________________________________________________
    1.34
    Conclusion
    1.32
    ________________________________
    1.32
    ----------------------------------------------------------------
    1.30
    --------------------
    1.27
    ------------------------------------------------
    1.26
    --------------------------------
    1.25
    -----------
    1.25
    Act Density 0.239%

    No Known Activations