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

    Neuronpedia

    INDEX
    Explanations

    syntactical structure in code-like formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inq
    -0.17
    ãĥ³ãĤ¯
    -0.15
    essian
    -0.15
    ogie
    -0.14
     Clo
    -0.14
    idan
    -0.14
    ecided
    -0.14
    forge
    -0.14
    igli
    -0.14
     sav
    -0.14
    POSITIVE LOGITS
    -www
    0.16
    íĥ
    0.15
    Verdana
    0.15
    acre
    0.15
    .DropTable
    0.15
    ÙĪÙĤÙģ
    0.14
    lund
    0.14
    noch
    0.14
     Rican
    0.14
     refin
    0.14
    Act Density 0.063%

    No Known Activations