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

    Neuronpedia

    INDEX
    Explanations

    references to the effects of different substances or interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bissau
    -1.00
    craper
    -0.95
    "}>
    -0.87
     stringBuilder
    -0.83
    تفصیلات
    -0.83
    »։
    -0.83
    ')")
    -0.82
    '}>
    -0.82
    bobox
    -0.80
    AccessFile
    -0.79
    POSITIVE LOGITS
     effects
    1.90
     Effects
    1.78
     effect
    1.70
    Effects
    1.70
     Effect
    1.64
    effects
    1.60
    Effect
    1.59
     EFFECTS
    1.53
    effect
    1.51
     EFFECT
    1.46
    Act Density 0.114%

    No Known Activations