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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different roles or positions in organizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate roles or positions held by individuals in various organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illin
    -0.78
    llah
    -0.77
    edu
    -0.75
    mort
    -0.71
    lass
    -0.70
    BR
    -0.69
    Reward
    -0.69
    root
    -0.68
    plate
    -0.68
    ouse
    -0.68
    POSITIVE LOGITS
    bidden
    0.91
    ked
    0.90
    geries
    0.87
    gotten
    0.84
     example
    0.83
     instance
    0.82
    gery
    0.81
    cers
    0.81
    aging
    0.80
     Misc
    0.79
    Act Density 0.109%

    No Known Activations