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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official announcements or statements

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     attrition
    -0.73
     unsuccessful
    -0.73
     disappointed
    -0.71
     disappoint
    -0.71
     disliked
    -0.70
     bothers
    -0.69
     weakest
    -0.67
    hement
    -0.67
     misses
    -0.67
     disappointing
    -0.67
    POSITIVE LOGITS
     now
    0.89
    now
    0.88
     seamlessly
    0.87
     instantly
    0.85
     accessible
    0.83
     possibilities
    0.81
     instant
    0.80
     effortlessly
    0.78
     democrat
    0.78
     triv
    0.77
    Act Density 0.659%

    No Known Activations