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

    Neuronpedia

    INDEX
    Explanations

    words related to illegal cooperation or scheming

    oai_token-act-pair · gpt-3.5-turbo

    terms related to collusion and complicity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beginner
    -0.75
     finishing
    -0.69
    èª
    -0.67
     Independence
    -0.67
    oya
    -0.66
     finish
    -0.65
     Paraly
    -0.65
    duration
    -0.64
     awards
    -0.64
     rainy
    -0.64
    POSITIVE LOGITS
     collusion
    2.50
     complicity
    2.31
     conspiring
    2.03
     complicit
    1.82
     nefarious
    1.76
     treason
    1.72
     conspir
    1.68
     sinister
    1.65
     infiltrated
    1.62
     treacher
    1.62
    Act Density 0.075%

    No Known Activations