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

    Neuronpedia

    INDEX
    Explanations

    instances of violence and physical assault

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.14
    1:0.01
    2:0.13
    3:0.06
    4:0.08
    5:0.05
    6:0.04
    7:0.04
    8:0.18
    9:0.07
    10:0.09
    11:0.07
    Negative Logits
    uyomi
    -2.00
     guiActiveUn
    -1.76
     Bulletin
    -1.62
     ageing
    -1.59
     relegation
    -1.57
     pione
    -1.56
     Vanguard
    -1.55
    odcast
    -1.55
     Dhabi
    -1.54
     Pulitzer
    -1.53
    POSITIVE LOGITS
    SPONSORED
    1.75
    nce
    1.70
    hered
    1.61
     them
    1.61
     Bulgar
    1.60
    isters
    1.60
    eers
    1.56
    undy
    1.55
    seek
    1.54
    lifting
    1.52
    Act Density 0.002%

    No Known Activations