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

    Neuronpedia

    INDEX
    Explanations

    words related to motor or gaming activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to motels and accommodations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lever
    -0.72
     Pepper
    -0.72
     Barbarian
    -0.72
     Yi
    -0.70
     Shanahan
    -0.69
     Sha
    -0.69
     Shant
    -0.69
     Schwar
    -0.69
     Barbar
    -0.68
     Shiva
    -0.66
    POSITIVE LOGITS
     mot
    3.78
    mot
    2.16
     sperm
    1.21
     MOT
    1.17
     gam
    1.09
     motel
    1.09
    fam
    1.04
     vo
    0.97
     conce
    0.93
     vag
    0.92
    Act Density 0.036%

    No Known Activations