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

    Neuronpedia

    INDEX
    Explanations

    language related to excitement and enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelSerializer
    -0.60
     StatefulWidget
    -0.57
    cisco
    -0.55
     diri
    -0.54
    اص
    -0.54
     واقع
    -0.53
    علق
    -0.53
    卑
    -0.53
     assemb
    -0.52
     οποίο
    -0.52
    POSITIVE LOGITS
    elemField
    0.89
     adanya
    0.86
     تانيه
    0.79
    Personendaten
    0.78
     gibts
    0.76
    ConstraintMaker
    0.73
     Réponses
    0.73
     eventuali
    0.72
    Tikang
    0.72
    esez
    0.71
    Act Density 0.385%

    No Known Activations