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

    Neuronpedia

    INDEX
    Explanations

    questions and statements about identity and personal expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.45
    :✨
    -0.42
     damn
    -0.41
    URLException
    -0.41
     shalt
    -0.41
     mogelijk
    -0.41
    unless
    -0.40
    tikzpicture
    -0.40
    ^(@)
    -0.40
    TypeID
    -0.39
    POSITIVE LOGITS
     Describe
    0.85
     describe
    0.80
    Describe
    0.79
     describir
    0.75
     proudest
    0.68
    describe
    0.68
     décrire
    0.64
     tell
    0.61
     Tell
    0.58
     advice
    0.57
    Act Density 0.191%

    No Known Activations