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

    Neuronpedia

    INDEX
    Explanations

    objects or things that are lying or found in various locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    gment
    -1.06
    wcs
    -1.01
    ãĤ¡
    -0.99
    gments
    -0.96
    ente
    -0.93
    Ī
    -0.92
    actic
    -0.91
    eme
    -0.90
     Cosponsors
    -0.88
    xual
    -0.88
    POSITIVE LOGITS
     beside
    1.26
     amongst
    1.23
     begging
    1.18
     somewhere
    1.17
     peacefully
    1.10
     atop
    1.08
     nude
    1.05
     Toad
    1.04
     upstairs
    1.03
     naked
    1.02
    Act Density 1.835%

    No Known Activations