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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.08
    3:0.04
    4:0.06
    5:0.02
    6:0.24
    7:0.12
    8:0.03
    9:0.03
    10:0.24
    11:0.05
    Negative Logits
    ㅋㅋ
    -1.78
    autions
    -1.74
    アル
    -1.74
    ------------
    -1.73
    カ
    -1.73
    EFF
    -1.67
    Child
    -1.65
    �
    -1.64
    チ
    -1.62
    isSpecialOrderable
    -1.61
    POSITIVE LOGITS
     fences
    1.72
     fencing
    1.70
     ledger
    1.66
     terminals
    1.65
     sediment
    1.64
     corridor
    1.62
     machinery
    1.61
     berth
    1.61
     pool
    1.61
     pathogens
    1.61
    Act Density 0.000%

    No Known Activations