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

    Neuronpedia

    INDEX
    Explanations

    quantitative phrases indicating quantities and groupings in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.21
    3:0.06
    4:0.06
    5:0.04
    6:0.11
    7:0.06
    8:0.03
    9:0.03
    10:0.07
    11:0.22
    Negative Logits
    ozo
    -1.65
    ーク
    -1.60
    ophob
    -1.57
     Deals
    -1.56
     weap
    -1.50
    ularity
    -1.50
    iren
    -1.49
     Mania
    -1.49
    inations
    -1.47
    govtrack
    -1.47
    POSITIVE LOGITS
    pell
    1.84
    transform
    1.63
    ram
    1.53
    uilt
    1.47
    github
    1.43
     stip
    1.43
    hetical
    1.43
    omething
    1.41
    thora
    1.41
    properties
    1.38
    Act Density 0.020%

    No Known Activations