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

    Neuronpedia

    INDEX
    Explanations

    references to violent crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.14
    3:0.07
    4:0.04
    5:0.02
    6:0.28
    7:0.16
    8:0.03
    9:0.03
    10:0.07
    11:0.05
    Negative Logits
    etheless
    -2.25
    theless
    -1.68
    anwhile
    -1.67
     "$:/
    -1.63
    ichever
    -1.52
     FANTASY
    -1.49
    ":""},{"
    -1.40
    forth
    -1.36
    soDeliveryDate
    -1.35
    iland
    -1.34
    POSITIVE LOGITS
    gery
    1.67
    ilation
    1.37
    phy
    1.31
    ission
    1.30
    Delivery
    1.27
    geries
    1.27
     Sacrifice
    1.26
     sed
    1.24
    iaz
    1.21
    Result
    1.19
    Act Density 0.001%

    No Known Activations