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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to exercising rights and powers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymes
    -0.77
    ½
    -0.70
    lines
    -0.65
    apest
    -0.62
    onto
    -0.61
    dylib
    -0.59
     Survivors
    -0.59
    fix
    -0.59
    ology
    -0.59
    opers
    -0.58
    POSITIVE LOGITS
     discretion
    1.35
     patience
    1.04
     leverage
    1.03
     restraint
    1.02
     dominion
    0.97
     influence
    0.92
     authority
    0.91
     jurisdiction
    0.90
     control
    0.90
     undue
    0.89
    Act Density 0.062%

    No Known Activations