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

    Neuronpedia

    INDEX
    Explanations

    references to online documents and their metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edium
    -0.16
    ÑĢаж
    -0.15
    robe
    -0.14
    ниÑģÑĤ
    -0.14
    ainer
    -0.14
    urat
    -0.14
     Garten
    -0.14
    iele
    -0.13
    cona
    -0.13
    ksi
    -0.13
    POSITIVE LOGITS
     Aeros
    0.19
     aeros
    0.17
     Nimbus
    0.15
    spin
    0.15
     snow
    0.15
     Polly
    0.15
     stom
    0.15
    409
    0.15
     affine
    0.15
     Nut
    0.14
    Act Density 0.023%

    No Known Activations