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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating coercion or being compelled

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.43
    crí
    -0.42
     mariposas
    -0.38
     embaj
    -0.38
     cielos
    -0.38
     delegación
    -0.37
     programação
    -0.35
     externi
    -0.35
     bienes
    -0.34
     Hvad
    -0.34
    POSITIVE LOGITS
     Forced
    1.47
    forced
    1.47
     forced
    1.46
    Forced
    1.37
     forcing
    1.10
     compelled
    1.06
    forcing
    1.06
     gezwungen
    1.02
    被迫
    0.99
     Compulsory
    0.93
    Act Density 0.413%

    No Known Activations