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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to breadth or inclusiveness

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of breadth or generality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LV
    -0.79
     Keeper
    -0.76
     Tycoon
    -0.76
    ICAN
    -0.72
     Disciple
    -0.67
    USD
    -0.66
     Mistress
    -0.66
     Million
    -0.66
    Fight
    -0.65
    Dialogue
    -0.64
    POSITIVE LOGITS
    sheet
    1.49
    sheets
    1.32
    ening
    1.12
    leaf
    1.11
     spectrum
    1.03
    sword
    1.02
     strokes
    0.98
    ened
    0.96
    side
    0.92
     swath
    0.86
    Act Density 0.024%

    No Known Activations