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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences of pain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.09
    2:0.07
    3:0.08
    4:0.09
    5:0.09
    6:0.09
    7:0.07
    8:0.08
    9:0.07
    10:0.08
    11:0.09
    Negative Logits
    letters
    -2.66
    auri
    -2.59
    oenix
    -2.40
    lines
    -2.25
    itals
    -2.25
    vell
    -2.24
    rin
    -2.23
    ources
    -2.22
    uine
    -2.20
    catentry
    -2.13
    POSITIVE LOGITS
     misunder
    2.55
     shenan
    2.52
     cheating
    2.23
     privilege
    2.19
     accidentally
    2.19
    soDeliveryDate
    2.17
    SPONSORED
    2.15
    bash
    2.15
    cheat
    2.15
     stuffing
    2.14
    Act Density 0.000%

    No Known Activations