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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating high quality or superiority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ment
    -0.17
    nt
    -0.16
    наÑĩе
    -0.15
    our
    -0.15
    ema
    -0.14
    zon
    -0.14
    abler
    -0.14
    anine
    -0.14
    /do
    -0.14
    (es
    -0.14
    POSITIVE LOGITS
    -notch
    0.22
    most
    0.19
    OLON
    0.18
    -rated
    0.17
    oley
    0.17
    thora
    0.16
    cott
    0.16
    ogr
    0.16
    -secret
    0.16
    pest
    0.15
    Act Density 0.061%

    No Known Activations