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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating action or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .pp
    -0.16
    rah
    -0.15
    iek
    -0.15
    acro
    -0.14
    alon
    -0.14
    :animated
    -0.14
    hora
    -0.14
    çݲ
    -0.14
     GENERIC
    -0.14
    بار
    -0.14
    POSITIVE LOGITS
     alot
    0.16
     lots
    0.16
    RelativeTo
    0.15
     Yue
    0.15
    ÐĴаж
    0.15
     nothing
    0.15
     quite
    0.15
    à¥įतन
    0.15
     subpoena
    0.14
    æķij
    0.14
    Act Density 0.009%

    No Known Activations