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

    Neuronpedia

    INDEX
    Explanations

    terms indicating likelihood or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ·»
    -0.16
    iset
    -0.15
    sek
    -0.15
     Reich
    -0.15
    ogan
    -0.14
    uu
    -0.13
    æĭĽ
    -0.13
    reff
    -0.13
    ãĤ¦ãĤ©
    -0.13
    esar
    -0.13
    POSITIVE LOGITS
     ********************************************************************************
    0.14
    -ever
    0.14
    cro
    0.14
     Eag
    0.13
     Tanz
    0.13
     Austr
    0.13
    çł´
    0.13
     ark
    0.13
    acen
    0.13
    .peek
    0.13
    Act Density 0.018%

    No Known Activations