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

    Neuronpedia

    INDEX
    Explanations

    references to research studies and articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sett
    -0.15
    istra
    -0.14
    ãģĭãĤĬ
    -0.14
    аÑĪа
    -0.14
    aval
    -0.14
    ÙĪÛĮÙĩ
    -0.14
    rei
    -0.13
    annes
    -0.13
    .field
    -0.13
    g
    -0.13
    POSITIVE LOGITS
     Mezi
    0.15
    posix
    0.14
     (↵↵
    0.14
    绩
    0.14
     witch
    0.14
     perceptions
    0.14
    taj
    0.13
     bundles
    0.13
    UILT
    0.13
    loven
    0.13
    Act Density 0.062%

    No Known Activations