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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or lack of knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.82
    GEBURTSDATUM
    -0.79
    WebElementEntity
    -0.79
    enterOuterAlt
    -0.77
    itinéraire
    -0.77
     NSCoder
    -0.77
    QMetaType
    -0.75
     tartalomajánló
    -0.74
     للمعارف
    -0.74
     <>",
    -0.74
    POSITIVE LOGITS
     want
    0.86
     I
    0.81
     know
    0.77
     think
    0.72
     hate
    0.64
     We
    0.63
     czu
    0.63
    I
    0.62
     we
    0.62
     am
    0.60
    Act Density 0.149%

    No Known Activations