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

    Neuronpedia

    INDEX
    Explanations

    positive sentiments and descriptions of pleasant experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mergeFrom
    -0.69
     nakalista
    -0.68
    InjectAttribute
    -0.67
    featureID
    -0.66
    PreInfinity
    -0.60
     المعيارى
    -0.60
     AspNetCore
    -0.59
     propOrder
    -0.59
    ="@+
    -0.59
     InputDecoration
    -0.58
    POSITIVE LOGITS
    addContainerGap
    0.63
     Gesamt
    0.59
     bagus
    0.58
     demais
    0.57
     nice
    0.57
    nice
    0.56
     spoluprá
    0.55
    ละ
    0.54
    Nice
    0.53
     légitime
    0.53
    Act Density 0.156%

    No Known Activations