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

    Neuronpedia

    INDEX
    Explanations

    terms related to eligibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.52
    <eos>
    -0.51
     Bod
    -0.49
     Rest
    -0.48
     Bo
    -0.46
     Sen
    -0.46
     professional
    -0.46
    ffichage
    -0.46
    knot
    -0.45
     pre
    -0.45
    POSITIVE LOGITS
     himſelf
    0.93
     الحره
    0.92
     itſelf
    0.92
    Hauptartikel
    0.89
     كومونز
    0.89
    eligible
    0.88
     themſelves
    0.86
     myſelf
    0.85
     виправивши
    0.85
    CloseOperation
    0.85
    Act Density 0.233%

    No Known Activations