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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of social or cultural inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickle
    -0.17
    lements
    -0.16
    ữ
    -0.16
    еле
    -0.15
    uard
    -0.15
    ago
    -0.14
    indh
    -0.14
    ÙıÙĪا
    -0.14
    .jms
    -0.13
    rie
    -0.13
    POSITIVE LOGITS
     Bench
    0.15
    aton
    0.14
    aeda
    0.14
    Large
    0.13
     Lambert
    0.13
    LAN
    0.13
    alat
    0.13
     dép
    0.13
    atin
    0.13
    иж
    0.13
    Act Density 0.007%

    No Known Activations