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

    Neuronpedia

    INDEX
    Explanations

    statements related to leadership and authority

    oai_token-act-pair · gpt-3.5-turbo

    expressions of leadership and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.63
    described
    -0.58
     Reported
    -0.57
    surprisingly
    -0.53
    translation
    -0.53
    published
    -0.53
    WC
    -0.53
    Published
    -0.51
    bilt
    -0.50
    ONDON
    -0.49
    POSITIVE LOGITS
     âĢ¦"
    1.01
    )."
    0.97
    âĢ¦"
    0.95
    !"
    0.94
     ..."
    0.94
    ..."
    0.89
    âĢ¦."
    0.87
    !!"
    0.86
    ?"
    0.85
    ?!"
    0.84
    Act Density 1.239%

    No Known Activations