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

    Neuronpedia

    INDEX
    Explanations

    references to participation or requirements involving specific conditions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gether
    -0.19
    neath
    -0.19
    INCLUDED
    -0.18
    stairs
    -0.18
    jourd
    -0.16
    forman
    -0.16
    semble
    -0.16
    theless
    -0.16
    ynchronously
    -0.15
    quoi
    -0.15
    POSITIVE LOGITS
    ypical
    0.28
    ech
    0.26
    elect
    0.26
    ype
    0.25
    emperature
    0.24
    emplate
    0.24
    ele
    0.24
    emp
    0.24
    ime
    0.24
    rophy
    0.23
    Act Density 0.049%

    No Known Activations