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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations, specifically related to airports and highways

    oai_token-act-pair · gpt-3.5-turbo

    references to financial costs and legal implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ').
    -1.02
    .):
    -0.94
    ?).
    -0.91
    !).
    -0.90
    '),
    -0.84
    .")
    -0.82
     toget
    -0.76
    !".
    -0.76
     tremend
    -0.76
    !),
    -0.75
    POSITIVE LOGITS
    ↵
    0.81
     Listen
    0.64
     Stephen
    0.63
     Justin
    0.62
     /*
    0.62
     TP
    0.61
    ↵↵
    0.61
     Casey
    0.58
     Peter
    0.58
     Kathleen
    0.57
    Act Density 0.318%

    No Known Activations