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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal behavior and fleeing from law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.13
    3:0.07
    4:0.19
    5:0.02
    6:0.11
    7:0.21
    8:0.02
    9:0.03
    10:0.08
    11:0.05
    Negative Logits
    CLASSIFIED
    -1.38
    SHIP
    -1.33
     persuasion
    -1.31
    ounge
    -1.30
     Programme
    -1.26
    EMP
    -1.23
    pired
    -1.21
     documentary
    -1.21
     specializing
    -1.21
    IGN
    -1.20
    POSITIVE LOGITS
    oline
    1.45
     rooft
    1.41
    onew
    1.40
     heights
    1.40
    }}}
    1.38
     woods
    1.31
     hills
    1.30
    mares
    1.29
     sack
    1.28
     castle
    1.28
    Act Density 0.009%

    No Known Activations