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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive emotions and motivational sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )=-\
    -0.68
     Severity
    -0.65
     severity
    -0.55
     darkness
    -0.54
     GenerationType
    -0.54
     Worst
    -0.54
    bibinfo
    -0.53
    kegaard
    -0.53
     eti
    -0.52
     warns
    -0.52
    POSITIVE LOGITS
     praises
    0.70
     jub
    0.68
     happier
    0.67
     praising
    0.66
    MessageTagHelper
    0.64
     praise
    0.63
     smiling
    0.62
     happy
    0.62
    PositiveButton
    0.62
    ագրություններ
    0.62
    Act Density 0.915%

    No Known Activations