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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recognition or identification of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.62
    <h3>
    -0.61
    ｙ
    -0.60
    AuthProvider
    -0.60
     Phillips
    -0.59
    גרת
    -0.58
    確認ください
    -0.58
     pac
    -0.57
    äť
    -0.56
     Raiders
    -0.56
    POSITIVE LOGITS
     KNOWN
    1.16
    KNOWN
    1.16
     Known
    1.15
     known
    1.11
    Known
    1.10
    known
    1.07
    complexContent
    0.97
    Portale
    0.97
     Bekannt
    0.96
     >=",
    0.94
    Act Density 0.088%

    No Known Activations