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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating leadership and influence within professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Diablo
    -0.16
     Dorothy
    -0.15
    monds
    -0.15
    349
    -0.15
    253
    -0.15
     bols
    -0.15
     Tig
    -0.15
    phies
    -0.14
    674
    -0.14
     Gins
    -0.14
    POSITIVE LOGITS
     Jamie
    1.19
    Jamie
    1.04
     jam
    0.98
    jam
    0.90
     Jam
    0.89
     jams
    0.79
    Jam
    0.77
     Jaime
    0.69
     jurisdiction
    0.66
     Jur
    0.63
    Act Density 0.007%

    No Known Activations