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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to a sense of permanence or continuity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a continuous or growing trend

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewed
    -0.66
    emia
    -0.63
     Anthem
    -0.61
     Cumm
    -0.61
     Obj
    -0.61
    ItemTracker
    -0.60
     Eug
    -0.59
     Legions
    -0.59
    aucus
    -0.58
     fellows
    -0.57
    POSITIVE LOGITS
    green
    1.13
    lasting
    1.05
    thing
    1.00
    more
    0.93
    theless
    0.90
    THING
    0.87
    things
    0.80
    day
    0.74
    last
    0.72
    increasing
    0.71
    Act Density 0.028%

    No Known Activations