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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and structural elements within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :+:
    -0.72
    pushFollow
    -0.65
     مؤرشف
    -0.56
    $.
    -0.55
    NSIndexPath
    -0.55
    -0.54
    USTAIN
    -0.53
    +#+#
    -0.53
    itudinal
    -0.52
    ricts
    -0.50
    POSITIVE LOGITS
     betweenstory
    0.63
    InjectAttribute
    0.63
     Roskov
    0.55
     ویکی‌پدی
    0.52
    ))
    0.52
     باخ
    0.49
    ok
    0.49
    IsMutable
    0.49
     Италијани
    0.49
     Signalez
    0.48
    Act Density 0.191%

    No Known Activations