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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of "conduct" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lash
    -0.17
    าย
    -0.17
    -0.17
    upon
    -0.17
    lings
    -0.16
    stell
    -0.16
    arch
    -0.15
    bia
    -0.15
    fan
    -0.15
    arching
    -0.15
    POSITIVE LOGITS
    eur
    0.23
    ors
    0.23
    icut
    0.22
    ance
    0.20
    ivities
    0.20
    eurs
    0.19
    ive
    0.18
    ees
    0.18
    ible
    0.17
    ivity
    0.16
    Act Density 0.018%

    No Known Activations