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

    Neuronpedia

    INDEX
    Explanations

    references to judgment or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imli
    -0.15
    Ã¤ÃŁ
    -0.15
    .GetAsync
    -0.15
    ÃĹ↵↵
    -0.14
    icus
    -0.14
    風
    -0.14
    изнеÑģ
    -0.14
    steller
    -0.14
    .Aggressive
    -0.14
    533
    -0.13
    POSITIVE LOGITS
    gram
    0.15
    plr
    0.15
    ude
    0.15
    aye
    0.14
    istik
    0.14
    ongs
    0.14
     unconditional
    0.14
     autos
    0.14
    uce
    0.14
     heavy
    0.14
    Act Density 0.006%

    No Known Activations