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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs related to an evaluation or opinion of something

    oai_token-act-pair · gpt-3.5-turbo

    assertions about significant truths or principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itures
    -0.81
    misc
    -0.71
    ideon
    -0.68
    aroo
    -0.68
    rams
    -0.67
     Delivery
    -0.67
    ramids
    -0.65
    ersion
    -0.64
    rn
    -0.62
     ..............
    -0.62
    POSITIVE LOGITS
     bothering
    0.85
     overlooked
    0.83
     distinguishing
    0.78
     noticeable
    0.77
     highlights
    0.76
     distinguishes
    0.75
     borne
    0.75
     unnoticed
    0.75
    oken
    0.75
     bothered
    0.73
    Act Density 0.216%

    No Known Activations