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

    Neuronpedia

    INDEX
    Explanations

    exclamatory punctuation and expressions of surprise or enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.76
    lict
    -0.68
    rational
    -0.67
    NetMessage
    -0.67
     boundaries
    -0.66
    relations
    -0.66
     arrang
    -0.66
    mine
    -0.66
    mates
    -0.65
    eki
    -0.65
    POSITIVE LOGITS
     exclaimed
    1.28
     exclaim
    1.18
    #$
    1.05
     yelled
    1.00
     shouted
    1.00
     yells
    0.92
     cried
    0.91
    @#&
    0.87
     screamed
    0.87
     shouts
    0.84
    Act Density 0.008%

    No Known Activations