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

    Neuronpedia

    INDEX
    Explanations

    dates written in "Oct" format

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Oct"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hou
    -0.71
    verson
    -0.63
     gravy
    -0.63
     destro
    -0.62
    LOCK
    -0.61
    ãĢı
    -0.60
    TRY
    -0.58
    vest
    -0.57
    ÃŃ
    -0.56
    ards
    -0.56
    POSITIVE LOGITS
     Oct
    3.60
    Oct
    2.87
     Sept
    2.31
     Nov
    2.31
     Aug
    2.30
     oct
    2.17
     Feb
    2.10
     Dec
    1.97
    oct
    1.96
    Sept
    1.94
    Act Density 0.009%

    No Known Activations