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

    Neuronpedia

    INDEX
    Explanations

    instances of notable achievements, events, or metrics associated with individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.07
    2:0.02
    3:0.10
    4:0.03
    5:0.39
    6:0.10
    7:0.02
    8:0.08
    9:0.07
    10:0.01
    11:0.01
    Negative Logits
     hereditary
    -2.27
     someday
    -2.16
     compartment
    -2.13
     analogy
    -2.13
    ascript
    -1.95
    quartered
    -1.94
    quote
    -1.93
     Jinn
    -1.93
    bard
    -1.92
     pseudonym
    -1.86
    POSITIVE LOGITS
     resurg
    2.33
     victories
    2.30
     highs
    2.28
     losses
    2.18
    mania
    2.17
     wins
    2.16
     contests
    2.08
     nominations
    2.06
     giveaways
    2.05
     totals
    2.04
    Act Density 0.986%

    No Known Activations