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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a small degree or amount of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate minor problems or criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idth
    -0.83
    iership
    -0.82
    abad
    -0.81
    itizen
    -0.78
    itivity
    -0.77
    apons
    -0.77
    ulkan
    -0.76
    psons
    -0.76
    ãĤ¢ãĥ«
    -0.73
     Liberation
    -0.73
    POSITIVE LOGITS
     tricky
    1.17
     confusing
    1.12
     bit
    1.11
     disappointing
    1.10
     scary
    1.09
     pricey
    1.08
     misleading
    1.05
     intimidating
    1.04
     awkward
    1.03
     odd
    1.03
    Act Density 0.042%

    No Known Activations