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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is acting independently or on their own

    oai_token-act-pair · gpt-3.5-turbo

    instances where individuals or entities act independently or autonomously

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lehem
    -0.78
    anwhile
    -0.78
    pherd
    -0.77
    gerald
    -0.76
    rus
    -0.76
    obar
    -0.75
    ishops
    -0.74
    raints
    -0.72
    wark
    -0.72
    ĸļ
    -0.71
    POSITIVE LOGITS
     accord
    1.07
     footing
    0.95
     behalf
    0.95
     initiative
    0.92
     dime
    0.92
     merits
    0.88
     doorstep
    0.79
     discretion
    0.79
    Cloud
    0.77
     terms
    0.77
    Act Density 0.028%

    No Known Activations