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

    Neuronpedia

    INDEX
    Explanations

    elements related to personal relationships and community dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     integrity
    -0.50
     quality
    -0.46
    integrity
    -0.44
     intent
    -0.42
    quality
    -0.42
     trygg
    -0.42
     sauber
    -0.40
    耐
    -0.40
    干净
    -0.40
     goed
    -0.39
    POSITIVE LOGITS
    featureID
    0.90
    ValueStyle
    0.88
     nahilalakip
    0.84
    Rhestr
    0.82
    kháu
    0.81
    SequentialGroup
    0.80
     >=",
    0.80
    principalTable
    0.79
     חיצוניים
    0.75
     Wiktionnaire
    0.74
    Act Density 0.239%

    No Known Activations