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

    Neuronpedia

    INDEX
    Explanations

    references to significant items or phenomena in a context suggesting analysis or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.39
    1:0.03
    2:0.10
    3:0.07
    4:0.04
    5:0.04
    6:0.03
    7:0.04
    8:0.04
    9:0.05
    10:0.09
    11:0.03
    Negative Logits
     pods
    -2.50
    Brave
    -2.23
    romeda
    -2.19
     upd
    -2.14
    Gy
    -2.14
    rons
    -2.13
    byss
    -2.10
     experiment
    -2.07
    mates
    -2.05
     Cran
    -2.04
    POSITIVE LOGITS
     references
    3.95
    reference
    3.61
     reference
    3.49
     referencing
    3.45
     mentions
    3.34
     Reference
    3.19
    Reference
    3.05
     References
    3.04
     mentioning
    2.99
     referenced
    2.95
    Act Density 0.002%

    No Known Activations