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

    Neuronpedia

    INDEX
    Explanations

    instances of emotional expression and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.59
    StructEnd
    -0.55
    win
    -0.53
     mukaan
    -0.52
     fédé
    -0.48
     dikutip
    -0.47
    #
    -0.46
     win
    -0.46
    ITHUB
    -0.46
    //
    -0.46
    POSITIVE LOGITS
     nod
    0.81
     smile
    0.79
     hiss
    0.79
     gasp
    0.78
     cry
    0.78
     blink
    0.77
     sob
    0.76
     grin
    0.76
     sigh
    0.76
     giggle
    0.74
    Act Density 0.387%

    No Known Activations