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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of change or modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vette
    -0.17
    essim
    -0.16
    ensa
    -0.16
    undi
    -0.16
    ÄĽÅ¾
    -0.14
    uguay
    -0.14
    ĽĦ
    -0.14
     thr
    -0.14
    ournaments
    -0.13
    ossa
    -0.13
    POSITIVE LOGITS
    hift
    0.18
    iates
    0.17
    cac
    0.15
    ÐĴÐIJ
    0.14
    ä»ĭ
    0.14
    ym
    0.14
    /add
    0.14
    åºĬ
    0.14
    /extensions
    0.14
    cover
    0.14
    Act Density 0.059%

    No Known Activations