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

    Neuronpedia

    INDEX
    Explanations

    words related to German or Swedish letters and specific names

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Gemini
    -0.66
    ibly
    -0.63
    naires
    -0.63
    ibility
    -0.62
    aneously
    -0.60
     blindness
    -0.60
    ibilities
    -0.59
     Hearts
    -0.58
     Cobra
    -0.58
     Chavez
    -0.57
    POSITIVE LOGITS
    zbek
    1.15
    ö
    1.02
    ller
    0.98
    ·
    0.95
    ¸
    0.95
    hl
    0.92
    rm
    0.92
    misc
    0.91
    vre
    0.90
    kk
    0.88
    Act Density 0.021%

    No Known Activations