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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atos
    -0.97
    een
    -0.86
    ator
    -0.86
    alion
    -0.83
    irth
    -0.82
    assian
    -0.81
    sworth
    -0.77
    pipe
    -0.77
    stuff
    -0.77
    hip
    -0.74
    POSITIVE LOGITS
     Wasserman
    0.99
     Fey
    0.84
     Schmidt
    0.77
     Debbie
    0.75
     Jarrett
    0.73
    xtap
    0.73
     Diane
    0.72
     Kelley
    0.71
     DeVos
    0.69
     Pelosi
    0.69
    Act Density 0.006%

    No Known Activations