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

    Neuronpedia

    INDEX
    Explanations

    references to statistical analysis or methodology in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     microw
    -0.45
     Vern
    -0.43
    ؤلاء
    -0.42
     GREY
    -0.41
     chubby
    -0.41
    PostInfinity
    -0.41
     celebs
    -0.40
     <=",
    -0.40
     Gyro
    -0.40
     cheeks
    -0.39
    POSITIVE LOGITS
    IsMutable
    0.57
    ArrowToggle
    0.46
    KommentareTeilen
    0.45
     ब्रेकडाउन
    0.42
    fjspx
    0.42
    aarrggbb
    0.42
    besondere
    0.41
    addPreferredGap
    0.41
    хьтан
    0.40
     relatively
    0.39
    Act Density 3.396%

    No Known Activations