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

    Neuronpedia

    INDEX
    Explanations

    phrases related to providing information or evidence

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "provide."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.80
     trim
    -0.64
     count
    -0.64
    Reloaded
    -0.62
    mite
    -0.62
    masters
    -0.61
    FACE
    -0.61
    schild
    -0.60
    geist
    -0.60
    grass
    -0.60
    POSITIVE LOGITS
    idence
    1.41
    idential
    1.24
    iders
    1.23
    isions
    1.20
    incial
    1.12
    ince
    1.11
    idently
    1.10
    iding
    1.09
    ided
    1.05
    idences
    1.04
    Act Density 0.026%

    No Known Activations