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

    Neuronpedia

    INDEX
    Explanations

    tentative or suggestive language that expresses uncertainty or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plen
    -0.16
    fk
    -0.16
    unct
    -0.15
    utters
    -0.14
    agements
    -0.14
    ikh
    -0.14
    959
    -0.14
    ifu
    -0.13
    estre
    -0.13
    iren
    -0.13
    POSITIVE LOGITS
    enty
    0.15
    ì¶Ķ
    0.15
    ิà¹Ģศษ
    0.15
     Reed
    0.14
    -none
    0.14
     Doe
    0.14
    eyse
    0.14
     pole
    0.14
    rint
    0.14
    -cookie
    0.14
    Act Density 0.266%

    No Known Activations