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

    Neuronpedia

    INDEX
    Explanations

    proper names, potentially female names

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riter
    -0.80
    undai
    -0.79
    alion
    -0.76
    ilit
    -0.76
    cffff
    -0.75
    cgi
    -0.74
    direction
    -0.74
     predec
    -0.73
    PDATE
    -0.73
     carbohyd
    -0.72
    POSITIVE LOGITS
     Mae
    1.37
     Marie
    1.33
     Louise
    1.19
    Marie
    1.18
     Lynn
    1.16
     Nicole
    1.16
     Rae
    1.16
     herself
    1.13
     Sue
    1.12
     Grace
    1.10
    Act Density 0.214%

    No Known Activations