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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating uncertainty or lack of confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assis
    -0.17
    ovich
    -0.16
    lah
    -0.15
     self
    -0.15
     Gam
    -0.14
    EMON
    -0.14
     seksi
    -0.14
    uco
    -0.14
    uncio
    -0.14
    cott
    -0.14
    POSITIVE LOGITS
    μί
    0.18
    olan
    0.15
    .nc
    0.14
    δÏĮν
    0.14
    isma
    0.14
    lude
    0.14
     UIControl
    0.14
    اعÙĬ
    0.14
    plen
    0.14
    ë¡Ŀ
    0.14
    Act Density 0.001%

    No Known Activations