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

    Neuronpedia

    INDEX
    Explanations

    references to sources and the reliability of information presented in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.06
    2:0.01
    3:0.10
    4:0.04
    5:0.09
    6:0.05
    7:0.02
    8:0.42
    9:0.06
    10:0.01
    11:0.02
    Negative Logits
    rats
    -2.07
     accomplishments
    -1.85
     victories
    -1.78
    ittered
    -1.74
    emale
    -1.70
     Anniversary
    -1.69
     rookies
    -1.68
     Beaut
    -1.68
    utenberg
    -1.67
     achievements
    -1.65
    POSITIVE LOGITS
     sourced
    2.28
     sources
    2.19
    source
    2.00
     source
    1.93
     contacted
    1.91
    href
    1.88
    available
    1.82
     MSM
    1.77
    radio
    1.73
     sourcing
    1.72
    Act Density 0.028%

    No Known Activations