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

    Neuronpedia

    INDEX
    Explanations

    references to specific proteins or components related to scientific studies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Dray
    -0.70
     bry
    -0.67
     Ing
    -0.66
    bry
    -0.65
    slides
    -0.62
    PRS
    -0.62
     Atiku
    -0.62
    antd
    -0.60
    CAM
    -0.59
     poto
    -0.58
    POSITIVE LOGITS
     GF
    1.48
    GF
    1.39
     Wheat
    1.12
    gf
    1.07
     wheat
    1.02
    Wheat
    1.01
     gf
    1.00
     //$
    0.98
     Girlfriend
    0.93
    حياته
    0.91
    Act Density 0.009%

    No Known Activations