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

    Neuronpedia

    INDEX
    Explanations

    references to destruction or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.13
    3:0.06
    4:0.14
    5:0.03
    6:0.13
    7:0.16
    8:0.04
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
    yip
    -1.48
    00200000
    -1.38
     aisle
    -1.30
    soDeliveryDate
    -1.24
     Owners
    -1.22
    apolis
    -1.21
     traveller
    -1.20
     favoured
    -1.19
    aceae
    -1.13
     favourable
    -1.13
    POSITIVE LOGITS
     slic
    1.54
    redd
    1.40
    Seg
    1.35
    lesh
    1.34
    cloth
    1.34
    gross
    1.26
    laughter
    1.25
    Paper
    1.24
     futures
    1.21
    mson
    1.20
    Act Density 0.000%

    No Known Activations