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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating results or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.75
    سطس
    -0.60
     Diſ
    -0.59
     surla
    -0.59
    AxisAlignment
    -0.58
    openqa
    -0.57
     Majefty
    -0.57
     Cæsar
    -0.56
    leggen
    -0.56
    ʲ
    -0.55
    POSITIVE LOGITS
     resulting
    0.77
    Corollary
    0.72
    RegistryLite
    0.67
     resultant
    0.65
    sequent
    0.65
    TypedDataSet
    0.62
     increase
    0.62
     resulted
    0.61
    Adele
    0.60
    parsedMessage
    0.59
    Act Density 0.152%

    No Known Activations