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

    Neuronpedia

    INDEX
    Explanations

    references to vague or unspecified concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sic
    -0.16
    (es
    -0.15
    ric
    -0.15
    ANGO
    -0.15
     pun
    -0.14
    .Native
    -0.14
    ritz
    -0.14
    axon
    -0.14
    lop
    -0.14
    ê¶ģ
    -0.13
    POSITIVE LOGITS
    anol
    0.15
    /from
    0.15
    244
    0.15
    iner
    0.14
    adir
    0.14
    ÑĸнÑĮ
    0.14
    erras
    0.14
    Äįit
    0.14
    amentos
    0.14
    ril
    0.14
    Act Density 0.096%

    No Known Activations