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

    Neuronpedia

    INDEX
    Explanations

    terms related to presenting or highlighting diversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sWith
    -0.24
    soever
    -0.21
    shot
    -0.20
    nya
    -0.19
    nt
    -0.19
    tor
    -0.18
    son
    -0.17
    acious
    -0.17
    most
    -0.17
    ìĿĦ
    -0.16
    POSITIVE LOGITS
    bread
    0.23
     latter
    0.21
    à¸ģาร
    0.19
    à¸ģารà¹Ģล
    0.18
    ãģªãģĦ
    0.18
    es
    0.17
    νομ
    0.17
    getAs
    0.17
    à¸ģารà¸ŀ
    0.17
    ettings
    0.16
    Act Density 0.042%

    No Known Activations