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

    Neuronpedia

    INDEX
    Explanations

    verbs related to resisting, defying, or opposing something

    oai_token-act-pair · gpt-3.5-turbo

    references to pressure, defiance, and compliance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ridor
    -0.74
    estones
    -0.72
    Ok
    -0.70
    gins
    -0.69
    estone
    -0.68
    uchi
    -0.65
    istan
    -0.64
    today
    -0.64
    ok
    -0.63
    emade
    -0.63
    POSITIVE LOGITS
     temptation
    1.43
     urge
    1.05
     adversity
    1.03
     tempt
    1.03
     pressure
    0.99
     dictates
    0.95
     tyranny
    0.95
     demands
    0.91
     pleas
    0.90
     bullies
    0.88
    Act Density 0.206%

    No Known Activations