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

    Neuronpedia

    INDEX
    Explanations

    names starting with "Jo" or variations of it

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    riter
    -0.79
    ypes
    -0.78
    GoldMagikarp
    -0.77
    PDATE
    -0.75
    ebus
    -0.74
     predec
    -0.74
    direction
    -0.74
    uyomi
    -0.74
    cgi
    -0.73
    cffff
    -0.73
    POSITIVE LOGITS
     Mae
    1.21
     Marie
    1.19
     Lynn
    1.17
     Louise
    1.08
     Nicole
    1.06
     Anne
    1.05
     herself
    1.04
     Rae
    1.02
     Devi
    0.99
     Sue
    0.99
    Act Density 0.220%

    No Known Activations