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

    Neuronpedia

    INDEX
    Explanations

    references to generic or common phrases related to crime and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.09
    3:0.05
    4:0.08
    5:0.02
    6:0.20
    7:0.30
    8:0.03
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
    ername
    -1.86
    reon
    -1.63
    estic
    -1.60
    cise
    -1.59
    uno
    -1.54
    yahoo
    -1.54
    ETA
    -1.54
    omever
    -1.52
    cerned
    -1.52
    �
    -1.51
    POSITIVE LOGITS
    �
    1.59
     revolving
    1.57
     attrition
    1.57
     swall
    1.57
    ipel
    1.57
     disadvantage
    1.54
     brut
    1.49
     escal
    1.48
    opoly
    1.48
     stalls
    1.44
    Act Density 0.001%

    No Known Activations