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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to statistics or ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.15
    1:0.14
    2:0.04
    3:0.05
    4:0.04
    5:0.17
    6:0.07
    7:0.03
    8:0.07
    9:0.04
    10:0.08
    11:0.07
    Negative Logits
     Telesc
    -1.76
     contra
    -1.73
     theat
    -1.69
     Coliseum
    -1.65
     lands
    -1.62
     Crescent
    -1.60
     Cavern
    -1.60
     Quad
    -1.58
     Aux
    -1.58
     coerc
    -1.58
    POSITIVE LOGITS
    undo
    2.06
    �
    1.90
    7601
    1.86
    ��
    1.79
    orio
    1.75
    PHOTOS
    1.75
    �
    1.72
    ��極
    1.70
    undown
    1.69
    chance
    1.69
    Act Density 0.001%

    No Known Activations