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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causality or reasons

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causation or relationships between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascus
    -0.86
    scribe
    -0.78
    ail
    -0.77
    mouth
    -0.76
    bage
    -0.75
    arez
    -0.75
    adesh
    -0.72
    umat
    -0.72
    rete
    -0.72
    soever
    -0.72
    POSITIVE LOGITS
     fact
    1.02
     inexper
    0.95
     methodological
    0.94
     differences
    0.90
     sheer
    0.90
     lack
    0.86
     ignorance
    0.85
     misunderstanding
    0.85
     familiarity
    0.84
     inertia
    0.84
    Act Density 0.236%

    No Known Activations