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

    Neuronpedia

    INDEX
    Explanations

    references to systemic issues and local geographical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.12
    3:0.08
    4:0.20
    5:0.03
    6:0.16
    7:0.19
    8:0.03
    9:0.03
    10:0.05
    11:0.04
    Negative Logits
     Ong
    -1.54
    20439
    -1.52
    ultimate
    -1.42
    dylib
    -1.39
    earchers
    -1.39
    liga
    -1.39
    emale
    -1.33
     Liberation
    -1.31
    onement
    -1.31
    Published
    -1.30
    POSITIVE LOGITS
     disadvantage
    1.58
     deprivation
    1.50
     recess
    1.47
     behaved
    1.46
     exagger
    1.45
     rough
    1.43
     prejudices
    1.41
     relaxed
    1.41
     intimidated
    1.40
     convention
    1.39
    Act Density 0.001%

    No Known Activations