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

    Neuronpedia

    INDEX
    Explanations

    instances and discussions about equivalence or similarity in values, attributes, or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĻeh
    -0.16
    emoc
    -0.15
    stairs
    -0.15
    UY
    -0.14
    doc
    -0.14
    sj
    -0.14
    tron
    -0.14
    inus
    -0.14
    taire
    -0.14
    UIT
    -0.14
    POSITIVE LOGITS
     Annunci
    0.17
    orney
    0.16
    æŀ
    0.16
    isd
    0.15
    ackle
    0.14
     Malone
    0.14
    SPATH
    0.14
     Shelf
    0.14
    ensch
    0.14
    inden
    0.14
    Act Density 0.066%

    No Known Activations