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

    Neuronpedia

    INDEX
    Explanations

    conditional and speculative phrases implying uncertainty or possibility

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

    Contractions with "d" and words about guessing

    np_acts-logits-general · gemini-2.0-flash

    would guess imagine suggest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.73
     '\\;'
    -0.61
     pronti
    -0.58
     CreateTagHelper
    -0.56
     دیکھیے
    -0.54
    CrossRef
    -0.54
    versiti
    -0.53
    صابة
    -0.53
     uſ
    -0.53
    StoreMessageInfo
    -0.52
    POSITIVE LOGITS
     wager
    0.88
     bet
    0.82
     guess
    0.80
     imagine
    0.77
     say
    0.74
     bets
    0.73
     guesses
    0.70
     hazard
    0.68
     argue
    0.66
    guess
    0.63
    Act Density 0.082%

    No Known Activations