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

    Neuronpedia

    INDEX
    Explanations

    superlative adjectives and phrases indicating extremity or the highest degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntOverflow
    -0.54
    Kjelder
    -0.52
     wireType
    -0.51
    躇
    -0.49
    üyada
    -0.48
     ElementRef
    -0.48
    Données
    -0.47
     drauf
    -0.47
    Koordinaten
    -0.45
    alagi
    -0.45
    POSITIVE LOGITS
     strongest
    0.90
     greatest
    0.88
     best
    0.88
     brightest
    0.85
     safest
    0.84
     smartest
    0.84
    best
    0.82
     largest
    0.82
     biggest
    0.82
     widest
    0.81
    Act Density 0.409%

    No Known Activations