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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating systematic processes or steps in methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ressources
    -0.62
    氓
    -0.61
     comprando
    -0.61
     Mulberry
    -0.57
     milled
    -0.56
     iscri
    -0.56
    Surviving
    -0.56
     banished
    -0.55
    Irrit
    -0.55
     shaved
    -0.55
    POSITIVE LOGITS
    การ
    0.95
     történ
    0.88
    多次
    0.85
     successful
    0.79
    ệc
    0.76
     erfolgt
    0.76
     direct
    0.76
    successful
    0.76
     การ
    0.75
    sự
    0.75
    Act Density 1.402%

    No Known Activations