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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate numerical comparisons and exclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BorderSide
    -0.65
    tenths
    -0.63
     للاسماء
    -0.62
     tartalomajánló
    -0.60
    ništvo
    -0.60
    achios
    -0.59
    ripsi
    -0.57
    astify
    -0.57
     للمعارف
    -0.55
    rieved
    -0.54
    POSITIVE LOGITS
    NameInMap
    0.55
     nahilalakip
    0.52
    IsContent
    0.52
     برانيه
    0.50
    elemField
    0.49
    UnusedPrivate
    0.46
     Италијани
    0.46
     cu
    0.45
     too
    0.45
    mente
    0.45
    Act Density 0.916%

    No Known Activations