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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "here."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ello
    -0.16
    er
    -0.16
    uko
    -0.15
    enko
    -0.14
    ned
    -0.14
    me
    -0.14
    sd
    -0.13
    owi
    -0.13
    .Cos
    -0.13
    iced
    -0.13
    POSITIVE LOGITS
    _firestore
    0.16
    esium
    0.14
    aft
    0.14
    ulan
    0.14
    achable
    0.14
    ãĥ³ãĤ¬
    0.14
    ãĥ³ãĤ¿
    0.13
    ulur
    0.13
    ³
    0.13
    271
    0.13
    Act Density 0.021%

    No Known Activations