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

    Neuronpedia

    INDEX
    Explanations

    words related to support, responsibility, or impact

    oai_token-act-pair · gpt-3.5-turbo

    the word "bearing" and its variants, often in the context of responsibilities or physical attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    committee
    -0.90
    apo
    -0.81
    opus
    -0.81
    inx
    -0.80
    trak
    -0.76
    nels
    -0.75
    anwhile
    -0.75
    ucky
    -0.72
    ocrates
    -0.71
    antha
    -0.69
    POSITIVE LOGITS
    weight
    0.77
    weights
    0.72
    pless
    0.71
    tto
    0.69
    maid
    0.69
    cies
    0.69
    beit
    0.68
     cub
    0.66
     borne
    0.65
     advis
    0.65
    Act Density 0.010%

    No Known Activations