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

    Neuronpedia

    INDEX
    Explanations

    exclamation marks indicating strong emotions

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory statements and expressions of enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ·
    -0.65
     fixtures
    -0.65
     relationships
    -0.64
    rational
    -0.64
     electrodes
    -0.63
     oils
    -0.62
     negatives
    -0.62
    mates
    -0.62
    anos
    -0.62
     enriched
    -0.61
    POSITIVE LOGITS
    #$
    0.93
     âĢķ
    0.84
     exclaimed
    0.79
     exclaim
    0.77
    azon
    0.75
    /"
    0.73
    >>\
    0.70
     Bundy
    0.68
    @#&
    0.68
     shouted
    0.67
    Act Density 0.027%

    No Known Activations