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

    Neuronpedia

    INDEX
    Explanations

    phrases or words indicating small amounts or degrees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.76
     незавершена
    -0.67
    APIView
    -0.63
    ExecuteReader
    -0.57
     Wyd
    -0.54
     Bishops
    -0.53
    godic
    -0.52
    masse
    -0.51
     Toll
    -0.50
    гови
    -0.50
    POSITIVE LOGITS
     Etwas
    0.93
     bit
    0.92
     کمی
    0.91
    Slightly
    0.90
     Slightly
    0.88
    Somewhat
    0.87
    slightly
    0.87
     trochę
    0.86
     bisschen
    0.86
     slightly
    0.85
    Act Density 0.088%

    No Known Activations