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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.64
    <h1>
    -0.46
     su
    -0.45
    <h2>
    -0.44
     bras
    -0.43
    </h2>
    -0.43
     trajets
    -0.41
     &$
    -0.41
    '
    -0.41
    ↵↵
    -0.40
    POSITIVE LOGITS
     Савезне
    0.92
    principalColumn
    0.92
     ſind
    0.88
     greateſt
    0.88
     myſelf
    0.86
     vectorstock
    0.84
     ویکی‌پدیا
    0.82
     themſelves
    0.82
    elemField
    0.80
     faſt
    0.80
    Act Density 2.128%

    No Known Activations