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

    Neuronpedia

    INDEX
    Explanations

    actions or events that demonstrate significant change or reaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    able
    -0.16
    aul
    -0.15
    avier
    -0.15
    xia
    -0.14
    oa
    -0.14
    ia
    -0.14
    oster
    -0.14
    uai
    -0.14
    ordo
    -0.14
    è
    -0.14
    POSITIVE LOGITS
    ness
    0.20
    ãĤĬ
    0.17
    /is
    0.17
    rale
    0.17
     initially
    0.16
    ihn
    0.16
    ëĭ¤ëĬĶ
    0.16
    ly
    0.16
    nt
    0.16
    s
    0.15
    Act Density 1.141%

    No Known Activations