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

    Neuronpedia

    INDEX
    Explanations

    mentions of rugs

    oai_token-act-pair · gpt-3.5-turbo

    references to rugs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yss
    -1.03
    ãĥīãĥ©ãĤ´ãĥ³
    -0.77
    ccording
    -0.68
     Contrast
    -0.64
     glac
    -0.62
    selection
    -0.61
     unfocusedRange
    -0.60
    uclear
    -0.59
     Sabha
    -0.58
     Witness
    -0.57
    POSITIVE LOGITS
    ugs
    1.06
     Slug
    0.89
    uese
    0.88
    gery
    0.84
    ging
    0.83
    ged
    0.82
    glers
    0.81
    poon
    0.78
     Bunny
    0.76
     Crate
    0.72
    Act Density 0.004%

    No Known Activations