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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols often found in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.08
    3:0.07
    4:0.04
    5:0.05
    6:0.38
    7:0.06
    8:0.05
    9:0.07
    10:0.05
    11:0.04
    Negative Logits
    shire
    -1.58
    ividual
    -1.57
     condem
    -1.42
     dehydration
    -1.38
     amusement
    -1.35
     pilgrimage
    -1.35
     defe
    -1.30
     Ced
    -1.29
     Hag
    -1.27
    ecause
    -1.26
    POSITIVE LOGITS
    actionDate
    1.74
    untled
    1.61
    �
    1.59
    SI
    1.57
    UTF
    1.55
    icio
    1.55
    м
    1.53
    raph
    1.53
    л
    1.51
    ゼ
    1.49
    Act Density 0.001%

    No Known Activations