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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future potential or predictive statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zamanda
    -0.64
    новниш
    -0.61
     osa
    -0.56
     perfons
    -0.54
     geslacht
    -0.53
    abung
    -0.53
     Gunter
    -0.52
     nyaman
    -0.52
     Nación
    -0.52
     női
    -0.52
    POSITIVE LOGITS
     ujednoznacz
    0.64
    DoubleQuotes
    0.63
    }`).
    0.61
    PMailer
    0.59
    olescence
    0.57
    lète
    0.56
    melons
    0.54
     تانيه
    0.53
    QPalette
    0.52
    thma
    0.52
    Act Density 0.786%

    No Known Activations