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

    Neuronpedia

    INDEX
    Explanations

    words related to academic degrees and titles

    oai_token-act-pair · gpt-3.5-turbo

    titles and qualifications of medical professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bumper
    -0.67
     twists
    -0.66
     vein
    -0.63
     increments
    -0.60
     gor
    -0.60
     ponies
    -0.59
    ").
    -0.58
     reminders
    -0.58
     outlets
    -0.58
     traps
    -0.58
    POSITIVE LOGITS
    .,
    0.82
    uably
    0.80
    jri
    0.74
    hedral
    0.73
     Schne
    0.70
    retty
    0.70
     PhD
    0.69
    icably
    0.68
    join
    0.68
    .;
    0.67
    Act Density 0.103%

    No Known Activations