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

    Neuronpedia

    INDEX
    Explanations

    phrases related to beliefs and teachings

    oai_token-act-pair · gpt-3.5-turbo

    references to ideals and philosophies, particularly in a socio-political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DR
    -0.78
    draw
    -0.77
    king
    -0.77
    GS
    -0.72
    upon
    -0.71
    Ward
    -0.70
    kes
    -0.70
    Query
    -0.69
    session
    -0.69
    de
    -0.68
    POSITIVE LOGITS
     ideals
    1.32
    yip
    0.80
     Machina
    0.74
    urities
    0.74
    hip
    0.74
    cape
    0.72
     values
    0.71
     beliefs
    0.70
     Jinn
    0.69
     stances
    0.69
    Act Density 0.013%

    No Known Activations