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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and their plural forms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ungal
    -0.18
    em
    -0.15
     Pillow
    -0.15
    олод
    -0.14
     Chamber
    -0.14
     Sinatra
    -0.14
     pillow
    -0.14
    mw
    -0.13
     Bis
    -0.13
     Butler
    -0.13
    POSITIVE LOGITS
    imes
    0.18
    áÅĻe
    0.16
    ehr
    0.15
    epam
    0.14
    awi
    0.14
    poÄįet
    0.14
    ifetime
    0.14
    าà¸ĺ
    0.14
    :animated
    0.14
    PerPixel
    0.14
    Act Density 0.008%

    No Known Activations