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

    Neuronpedia

    INDEX
    Explanations

    titles or positions within organizations

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles associated with leadership or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     timetable
    -0.74
     routine
    -0.69
     breeze
    -0.67
     sponge
    -0.67
     save
    -0.64
     limitless
    -0.60
     saved
    -0.59
     Colleges
    -0.59
     frig
    -0.57
     fullest
    -0.57
    POSITIVE LOGITS
    uably
    0.86
    director
    0.79
     emer
    0.78
    =]
    0.75
    berus
    0.72
    ociate
    0.72
     Managing
    0.70
    itatively
    0.67
    conservancy
    0.66
    byss
    0.66
    Act Density 0.154%

    No Known Activations