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

    Neuronpedia

    INDEX
    Explanations

    references to steps or processes in a sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    est
    -0.15
    mos
    -0.14
     dirig
    -0.14
     Smy
    -0.14
    onde
    -0.13
    ủi
    -0.13
    rame
    -0.13
    ustos
    -0.13
    upil
    -0.13
    onio
    -0.13
    POSITIVE LOGITS
    AREN
    0.16
    chin
    0.15
    ãĥ¬ãĥĥãĥĪ
    0.15
    ãĤ¶ãĥ¼
    0.15
    asant
    0.14
    .BLL
    0.14
    è¡
    0.14
    arent
    0.14
    acus
    0.14
    ritz
    0.14
    Act Density 0.035%

    No Known Activations