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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conclusions or endings in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lick
    -0.15
    jt
    -0.15
    Ñĸдно
    -0.14
    jd
    -0.14
    abel
    -0.14
    _INTR
    -0.14
    atri
    -0.13
    à¥Ĥड
    -0.13
    ulty
    -0.13
    ÑĭÑĪ
    -0.13
    POSITIVE LOGITS
     Scope
    0.15
    mov
    0.14
    enville
    0.14
    VES
    0.14
    νÏĮ
    0.14
    oblin
    0.14
     Kob
    0.14
     Klo
    0.14
     two
    0.14
    ingly
    0.14
    Act Density 0.070%

    No Known Activations