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

    Neuronpedia

    INDEX
    Explanations

    specific entities, such as names, titles, and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     corpus
    -0.17
    squ
    -0.15
    648
    -0.15
    afia
    -0.15
    ãĥ¼ãĥł
    -0.14
     Ñĥгл
    -0.14
     repr
    -0.14
    afa
    -0.14
    _dump
    -0.14
    hood
    -0.14
    POSITIVE LOGITS
    BOOLE
    0.16
    /DD
    0.14
    hop
    0.14
    ontent
    0.14
    ffen
    0.13
    ãĤ¿ãĥ«
    0.13
     Linh
    0.13
    ominated
    0.13
    tn
    0.13
    elli
    0.13
    Act Density 0.243%

    No Known Activations