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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating outcomes or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    انه
    -0.57
     Ar
    -0.52
    semantics
    -0.47
     Rock
    -0.44
    　　……
    -0.44
     formal
    -0.43
    ):=\
    -0.42
     hand
    -0.42
    []){
    -0.42
    ті
    -0.41
    POSITIVE LOGITS
    MLLoader
    0.81
    matchCondition
    0.80
    ագրություններ
    0.78
    AutoresizingMask
    0.71
     Roskov
    0.70
    WriteBarrier
    0.67
    clusal
    0.65
    invokeLater
    0.65
    ArrowToggle
    0.65
    RegistryLite
    0.64
    Act Density 0.520%

    No Known Activations