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

    Neuronpedia

    INDEX
    Explanations

    mentions of unethical or illegal activities and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.07
    2:0.02
    3:0.08
    4:0.03
    5:0.08
    6:0.10
    7:0.35
    8:0.06
    9:0.05
    10:0.02
    11:0.04
    Negative Logits
    ascript
    -2.81
    itely
    -2.16
    epad
    -2.16
     Advis
    -2.14
    apter
    -2.06
     Panasonic
    -2.02
    batch
    -2.00
    illac
    -1.98
    DK
    -1.96
    olas
    -1.96
    POSITIVE LOGITS
     corruption
    3.20
     suicides
    3.11
     poisoning
    2.99
     earthquakes
    2.99
     malf
    2.95
     thefts
    2.95
     crime
    2.94
     accidents
    2.93
     murder
    2.88
     homicides
    2.88
    Act Density 0.521%

    No Known Activations