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

    Neuronpedia

    INDEX
    Explanations

    statements indicating outcomes or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thing
    -0.17
    ish
    -0.17
    est
    -0.16
    idge
    -0.15
    ertz
    -0.14
    former
    -0.14
    eli
    -0.14
    essler
    -0.14
    esh
    -0.13
     Lei
    -0.13
    POSITIVE LOGITS
    ively
    0.21
    agli
    0.17
    ogle
    0.17
    antly
    0.17
    ModelIndex
    0.16
    çuk
    0.16
    aneously
    0.15
    uate
    0.14
    antro
    0.14
    iveness
    0.14
    Act Density 0.043%

    No Known Activations