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

    Neuronpedia

    INDEX
    Explanations

    citation formats or references in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aad
    -0.16
    onta
    -0.15
    /end
    -0.15
    vida
    -0.14
    foot
    -0.14
    elight
    -0.14
    ayload
    -0.14
    recht
    -0.13
    .labels
    -0.13
    492
    -0.13
    POSITIVE LOGITS
    Ŀ
    0.15
    oves
    0.15
    ieres
    0.14
    ูล
    0.14
    chg
    0.13
    yal
    0.13
    kes
    0.13
    èİ
    0.13
    .opend
    0.13
    utf
    0.12
    Act Density 0.001%

    No Known Activations