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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to flaws or shortcomings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    foot
    -0.17
    nbsp
    -0.16
    holder
    -0.16
    ën
    -0.16
    quot
    -0.15
    nder
    -0.15
    thane
    -0.15
    holders
    -0.15
    ittings
    -0.15
    ầu
    -0.15
    POSITIVE LOGITS
    ively
    0.58
    ive
    0.41
    ives
    0.35
    iveness
    0.35
    ual
    0.34
    ors
    0.33
    ivity
    0.32
    ible
    0.30
    ually
    0.27
    IVE
    0.26
    Act Density 0.102%

    No Known Activations