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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to opposite ends, extremes, or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to the concept of "ends" or "ends" of objects or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dinand
    -0.68
     Flavoring
    -0.66
     Courage
    -0.65
     exceptional
    -0.63
     irregular
    -0.63
    PDATE
    -0.62
    issance
    -0.61
     opportunity
    -0.61
    atoon
    -0.60
     unusual
    -0.60
    POSITIVE LOGITS
    angering
    1.21
    owment
    1.12
    ocrine
    1.02
    ocrin
    1.00
    angers
    0.95
    game
    0.91
    angered
    0.85
    omorph
    0.83
    omet
    0.83
    games
    0.81
    Act Density 0.046%

    No Known Activations