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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tasks and deadlines

    oai_token-act-pair · gpt-3.5-turbo

    infinitive phrases indicating goals or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.69
     wastes
    -0.65
    ienne
    -0.63
     surges
    -0.57
    hops
    -0.54
     vows
    -0.54
    hai
    -0.53
    Orig
    -0.53
    awei
    -0.52
     viruses
    -0.52
    POSITIVE LOGITS
     satisfy
    1.15
     accommodate
    1.08
     accompany
    1.05
     contend
    1.05
     ensure
    1.03
     fill
    1.03
     give
    1.02
    ggles
    1.01
    wered
    1.01
     settle
    1.00
    Act Density 0.262%

    No Known Activations