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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political power or authority

    oai_token-act-pair · gpt-3.5-turbo

    references to authority or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eor
    -0.66
     Alvarez
    -0.66
    Sil
    -0.65
     Absent
    -0.64
    Gil
    -0.64
    rian
    -0.63
     Murd
    -0.62
    ded
    -0.61
     Tud
    -0.61
     Ign
    -0.61
    POSITIVE LOGITS
     powers
    1.02
    Reviewer
    0.92
    hell
    0.90
    uits
    0.84
     delegated
    0.82
     superpower
    0.81
     conferred
    0.79
    oshenko
    0.75
    wu
    0.72
    olve
    0.72
    Act Density 0.013%

    No Known Activations