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

    Neuronpedia

    INDEX
    Explanations

    exclamatory phrases indicating strong emotions

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory punctuation marks, particularly variations of the exclamation mark

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     manif
    -0.91
     destro
    -0.81
    yrus
    -0.80
    idon
    -0.78
     livest
    -0.76
    stem
    -0.74
    mos
    -0.73
     neighb
    -0.72
     pools
    -0.72
     quir
    -0.72
    POSITIVE LOGITS
    @#&
    1.19
    #$
    1.19
    @#
    1.07
    ?!
    1.02
     :)
    0.94
     Surely
    0.90
     Again
    0.89
     :-)
    0.87
     ðŁĻĤ
    0.87
     Please
    0.87
    Act Density 0.071%

    No Known Activations