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

    Neuronpedia

    INDEX
    Explanations

    references to population and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.06
    3:0.04
    4:0.16
    5:0.02
    6:0.04
    7:0.40
    8:0.02
    9:0.02
    10:0.08
    11:0.08
    Negative Logits
    ibur
    -1.70
     causation
    -1.69
     guiActiveUn
    -1.63
     grounding
    -1.62
    izont
    -1.59
     omission
    -1.57
     plummet
    -1.56
     ratification
    -1.55
    ratulations
    -1.52
     divest
    -1.51
    POSITIVE LOGITS
    ▬
    1.58
    houses
    1.55
    rose
    1.54
    eric
    1.46
    arus
    1.43
    keys
    1.40
     Word
    1.36
    ategories
    1.35
     Castle
    1.34
     Towns
    1.32
    Act Density 0.003%

    No Known Activations