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

    Neuronpedia

    INDEX
    Explanations

    items and phrases related to accountability and transparency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asca
    -0.15
    kov
    -0.15
    thag
    -0.15
    itos
    -0.15
    atı
    -0.14
    ringe
    -0.14
    âĶĺ
    -0.14
    審
    -0.14
    awks
    -0.14
    alian
    -0.13
    POSITIVE LOGITS
    ibble
    0.16
    pez
    0.16
     Arthropoda
    0.15
    ymm
    0.15
    923
    0.14
    ãĤ¿ãĥ¼
    0.14
    ortal
    0.14
    MING
    0.14
    ALCHEMY
    0.13
    Campaign
    0.13
    Act Density 0.002%

    No Known Activations