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

    Neuronpedia

    INDEX
    Explanations

    words related to news headlines and captions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Close" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    代
    -0.79
    uca
    -0.79
    stood
    -0.77
    iosyncr
    -0.72
    utical
    -0.71
    oplan
    -0.71
    umping
    -0.67
    iage
    -0.65
     includ
    -0.63
    flat
    -0.63
    POSITIVE LOGITS
     Close
    0.92
     Thumbnails
    0.80
     Annotations
    0.75
     Cait
    0.70
    querque
    0.66
    ################################
    0.65
    VERTISEMENT
    0.64
    ++++++++++++++++
    0.63
    Las
    0.62
    âĸ¬âĸ¬
    0.61
    Act Density 0.007%

    No Known Activations