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

    Neuronpedia

    INDEX
    Explanations

    exclamatory statements in text

    oai_token-act-pair · gpt-3.5-turbo

    exclamation marks used for emphasis or excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yrus
    -0.88
    undai
    -0.83
    idon
    -0.77
    itated
    -0.75
    mos
    -0.70
     footing
    -0.70
     brig
    -0.68
    vati
    -0.68
     condem
    -0.67
     restraints
    -0.67
    POSITIVE LOGITS
    @#&
    1.46
     :)
    1.10
    ?!
    1.05
     :-)
    1.03
    #$
    1.00
     ;)
    0.96
     ðŁĻĤ
    0.93
     Whilst
    0.90
     Come
    0.86
    @#
    0.86
    Act Density 0.070%

    No Known Activations