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

    Neuronpedia

    INDEX
    Explanations

    terms related to cumulative amounts or totals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cumulative and aggregate metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ournal
    -0.86
    asha
    -0.83
    kers
    -0.79
    geon
    -0.79
    yer
    -0.79
    chers
    -0.76
    neys
    -0.74
    hod
    -0.74
    OCK
    -0.72
    ket
    -0.71
    POSITIVE LOGITS
    ulative
    1.09
     cumulative
    0.95
     effect
    0.84
     effects
    0.78
     upkeep
    0.77
     incidence
    0.74
     coh
    0.74
     dose
    0.74
    Effects
    0.73
     probabilities
    0.73
    Act Density 0.010%

    No Known Activations