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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and related sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.59
    GTCX
    -0.58
    GIVEREF
    -0.48
    
    -0.46
    arrêter
    -0.46
    ագրություններ
    -0.45
    ftagPool
    -0.45
    ientras
    -0.44
     capucha
    -0.43
    $_['
    -0.42
    POSITIVE LOGITS
    はじめに
    0.57
     виправивши
    0.50
     @"/
    0.41
    InjectAttribute
    0.39
    </caption>
    0.39
    AnchorStyles
    0.38
    LookAnd
    0.37
    WillAppear
    0.36
    )++;
    0.36
    تم
    0.36
    Act Density 0.746%

    No Known Activations