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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating large quantities or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    󠁴
    -0.72
    󠁢
    -0.63
    TAWA
    -0.62
     Paglinawan
    -0.59
    μφωνα
    -0.58
    KEYCODE
    -0.58
     препратки
    -0.58
     stepwise
    -0.58
    μως
    -0.58
    AndEndTag
    -0.55
    POSITIVE LOGITS
     majority
    1.02
     many
    0.95
     maioria
    0.90
    majority
    0.87
     plupart
    0.83
     çoğu
    0.82
    大部分
    0.81
     majorité
    0.81
     большин
    0.80
     MANY
    0.79
    Act Density 0.373%

    No Known Activations