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

    Neuronpedia

    INDEX
    Explanations

    instances of significant events or actions taking place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.07
    3:0.09
    4:0.09
    5:0.07
    6:0.08
    7:0.08
    8:0.07
    9:0.07
    10:0.08
    11:0.09
    Negative Logits
    croft
    -1.99
    laws
    -1.95
     CRC
    -1.67
     SAS
    -1.58
    bledon
    -1.57
    leaf
    -1.53
    anse
    -1.47
     +---
    -1.46
    IER
    -1.46
    aska
    -1.45
    POSITIVE LOGITS
    ?」
    1.69
     favor
    1.66
     enrich
    1.56
     sparing
    1.55
     favour
    1.54
     flourish
    1.45
     expressed
    1.44
     appreciated
    1.44
     crave
    1.43
     Enhance
    1.41
    Act Density 0.000%

    No Known Activations