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

    Neuronpedia

    INDEX
    Explanations

    technical or specific terms related to features or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illard
    -0.19
    ills
    -0.17
    elda
    -0.17
    enia
    -0.15
    REA
    -0.15
    apiro
    -0.15
    rea
    -0.15
    aby
    -0.15
    istas
    -0.15
    ĤŃ
    -0.14
    POSITIVE LOGITS
    afil
    0.17
    ÏİÏĥειÏĤ
    0.15
    edBy
    0.14
    æĥł
    0.14
     Comet
    0.14
    aml
    0.14
     pasado
    0.14
    antis
    0.14
    ubb
    0.14
    aģı
    0.13
    Act Density 0.020%

    No Known Activations