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

    Neuronpedia

    INDEX
    Explanations

    references to individuals in assistant positions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various types of assistants, particularly in professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stakes
    -0.82
    abiding
    -0.80
    ibal
    -0.74
    Winged
    -0.72
    ename
    -0.72
    ERO
    -0.68
    igation
    -0.68
    ktop
    -0.68
    cale
    -0.67
    isky
    -0.67
    POSITIVE LOGITS
     professor
    1.10
     superintendent
    1.01
     secretary
    1.01
     director
    0.96
     principal
    0.94
     dean
    0.92
     secretaries
    0.91
     manager
    0.91
     pastor
    0.89
     treasurer
    0.88
    Act Density 0.033%

    No Known Activations