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

    Neuronpedia

    INDEX
    Explanations

    exclamatory statements expressing strong emotions

    oai_token-act-pair · gpt-3.5-turbo

    exclamation marks indicating strong emotions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conduc
    -0.84
    rament
    -0.73
    urai
    -0.70
    undai
    -0.69
    reen
    -0.66
     destro
    -0.66
    senal
    -0.66
    idon
    -0.64
    mine
    -0.64
     utilitarian
    -0.63
    POSITIVE LOGITS
    @#&
    1.37
    #$
    1.23
    ?!
    1.14
    @#
    1.08
    ãĢį
    1.03
    important
    0.90
     Surely
    0.82
     Needless
    0.78
     Anyway
    0.78
     Isn
    0.78
    Act Density 0.068%

    No Known Activations