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

    Neuronpedia

    INDEX
    Explanations

    mentions of time durations or specific time units like years

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, particularly commas, in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NK
    -0.70
    obin
    -0.68
    itionally
    -0.67
    oir
    -0.65
    cott
    -0.65
    TM
    -0.64
    utral
    -0.63
    adan
    -0.63
    cro
    -0.62
    FP
    -0.62
    POSITIVE LOGITS
     diminishing
    0.67
     decap
    0.62
    FontSize
    0.61
     recomm
    0.60
     neglected
    0.59
     Minotaur
    0.58
     announ
    0.58
     prosec
    0.56
     tacit
    0.55
    âĵĺ
    0.55
    Act Density 0.384%

    No Known Activations