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

    Neuronpedia

    INDEX
    Explanations

    verbs related to various forms of assessment or judgment

    oai_token-act-pair · gpt-3.5-turbo

    verbs and actions related to questioning, arguing, and exploring concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ajo
    -0.60
    ugu
    -0.55
    ggles
    -0.53
     Sierra
    -0.52
    rouse
    -0.51
    rise
    -0.50
     flu
    -0.49
    Us
    -0.49
    dos
    -0.49
    dom
    -0.49
    POSITIVE LOGITS
    omorphic
    0.68
     aback
    0.64
    urated
    0.63
     psychiat
    0.62
    DragonMagazine
    0.59
    entious
    0.57
    IRED
    0.57
    uzz
    0.56
     hostage
    0.56
    ivating
    0.56
    Act Density 0.727%

    No Known Activations