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

    Neuronpedia

    INDEX
    Explanations

    random hexadecimal characters and surrounding text

    oai_token-act-pair · gpt-3.5-turbo

    the presence of whitespace characters or the end of lines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rolet
    -0.66
     guiActiveUnfocused
    -0.63
     compromise
    -0.62
    nesday
    -0.62
    creen
    -0.62
     easing
    -0.62
    boro
    -0.61
     general
    -0.61
    wagen
    -0.61
     ease
    -0.61
    POSITIVE LOGITS
    ________________________________________________________________
    1.05
    ---------------
    0.93
    ~~~~~~~~~~~~~~~~
    0.93
    ------------------------
    0.91
    ------------
    0.91
    ÃĤ
    0.91
    à¸
    0.88
    Ëľ
    0.87
    ................................
    0.87
    ~~
    0.87
    Act Density 0.003%

    No Known Activations