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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inaction or failure to act

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asca
    -0.19
    .mvp
    -0.15
    oplan
    -0.14
     lur
    -0.14
    uliar
    -0.14
    919
    -0.14
    PressEvent
    -0.14
    nnen
    -0.14
    573
    -0.14
     Truy
    -0.14
    POSITIVE LOGITS
     nothing
    0.90
    nothing
    0.79
     Nothing
    0.79
     NOTHING
    0.75
    Nothing
    0.72
     nada
    0.65
     nichts
    0.59
     rien
    0.57
     ниÑĩего
    0.50
     nulla
    0.44
    Act Density 0.255%

    No Known Activations