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

    Neuronpedia

    INDEX
    Explanations

    words related to actions in both a literal and figurative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    quid pro quo, ends meet, well done, déjà vu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.65
    ագրություններ
    -0.62
    //
    -0.61
    anyahu
    -0.60
    رشف
    -0.60
    findpost
    -0.59
    MLLoader
    -0.59
    ſhip
    -0.59
     HasFactory
    -0.58
     Paglinawan
    -0.58
    POSITIVE LOGITS
     we
    0.34
     well
    0.33
     ajudá
    0.32
     next
    0.31
    <bos>
    0.30
     very
    0.29
     mid
    0.29
     comes
    0.28
     come
    0.28
     being
    0.28
    Act Density 0.039%

    No Known Activations