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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conditionality or dependency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thâu
    -0.72
    SQLiteDatabase
    -0.70
    dflare
    -0.67
    脚注の使い方
    -0.66
    apimachinery
    -0.65
     Bradbury
    -0.64
    Ljava
    -0.63
     Lucy
    -0.63
    Crm
    -0.63
     Weinberg
    -0.61
    POSITIVE LOGITS
     depending
    1.92
    depending
    1.83
    Depending
    1.77
     Depending
    1.75
     Depends
    1.45
     depends
    1.42
     dependiendo
    1.38
    depends
    1.35
     depend
    1.21
    Depends
    1.20
    Act Density 0.084%

    No Known Activations