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

    Neuronpedia

    INDEX
    Explanations

    exclamations

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     manif
    -0.85
     surpr
    -0.85
    ylum
    -0.77
     destro
    -0.76
    undai
    -0.76
     arrang
    -0.75
     glim
    -0.72
     condem
    -0.71
    Ö¼
    -0.71
     restraints
    -0.70
    POSITIVE LOGITS
    @#&
    1.33
    #$
    1.11
    ?!
    0.90
    @#
    0.87
    important
    0.86
     Featuring
    0.79
     Shine
    0.78
     Euph
    0.78
    NOW
    0.78
     Come
    0.77
    Act Density 0.058%

    No Known Activations