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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals holding positions as assistants

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of assistants and assistant roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atche
    -0.76
    stakes
    -0.73
    abouts
    -0.72
    ERO
    -0.70
    igation
    -0.69
    abiding
    -0.68
    bows
    -0.68
    eta
    -0.68
    ards
    -0.66
    arium
    -0.66
    POSITIVE LOGITS
     professor
    0.97
     pastor
    0.80
     coaches
    0.79
     assistant
    0.79
     secretary
    0.74
     coach
    0.73
     secretaries
    0.72
     teacher
    0.72
     preacher
    0.72
    iliary
    0.70
    Act Density 0.030%

    No Known Activations