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

    Neuronpedia

    INDEX
    Explanations

    references to global or world contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zelf
    -0.19
    ety
    -0.17
    cht
    -0.17
    imson
    -0.16
    elor
    -0.16
    aign
    -0.15
    ToWorld
    -0.15
    ersen
    -0.15
    elow
    -0.14
    à¹Ģà¸ģล
    -0.14
    POSITIVE LOGITS
    Wide
    0.34
    -wide
    0.33
     Wide
    0.30
    wide
    0.30
    liness
    0.29
     wide
    0.29
    views
    0.26
    -ren
    0.26
    iyon
    0.19
    -class
    0.19
    Act Density 0.086%

    No Known Activations