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

    Neuronpedia

    INDEX
    Explanations

    phrases describing a quantity or a specific group of items

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to categories, instances, or classes of items or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abus
    -0.80
    osate
    -0.77
    Spoiler
    -0.74
    uberty
    -0.71
    endon
    -0.71
    slaught
    -0.70
     Canaver
    -0.69
    obook
    -0.69
    rium
    -0.69
    isconsin
    -0.69
    POSITIVE LOGITS
     things
    1.05
     items
    1.00
     types
    0.99
     kinds
    0.99
     pesky
    0.96
     occasions
    0.95
     entities
    0.95
     cases
    0.95
     situations
    0.94
     categories
    0.94
    Act Density 0.109%

    No Known Activations