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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe methods or approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.98
     Majefty
    -0.97
     Mahmud
    -0.96
    ScreenState
    -0.96
     pleaſure
    -0.94
     Schulte
    -0.94
     ―――――
    -0.94
     McNeil
    -0.93
    Datuak
    -0.93
    ölkerung
    -0.93
    POSITIVE LOGITS
     Way
    1.81
     way
    1.78
     WAY
    1.76
    Way
    1.64
     ways
    1.63
    way
    1.57
     Ways
    1.55
     WAYS
    1.45
    Ways
    1.41
    WAY
    1.41
    Act Density 0.081%

    No Known Activations