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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical actions or events happening

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical and symbolic formatting or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uly
    -0.76
     conferred
    -0.71
    intendent
    -0.68
     CJ
    -0.67
     enshr
    -0.65
     afforded
    -0.65
    andum
    -0.65
    outube
    -0.65
     union
    -0.64
    ocket
    -0.63
    POSITIVE LOGITS
    Haunted
    0.88
     thriller
    0.84
    ogun
    0.83
    Fear
    0.83
    RPG
    0.82
    ARR
    0.80
    ?????-?????-
    0.78
    Untitled
    0.78
    ?????-
    0.74
     Reloaded
    0.74
    Act Density 0.095%

    No Known Activations