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

    Neuronpedia

    INDEX
    Explanations

    phrases related to regulations and guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aqu
    -0.15
    ÏīÏĤ
    -0.15
    amac
    -0.15
    holes
    -0.14
    eron
    -0.14
    mill
    -0.14
    idia
    -0.13
    shadow
    -0.13
    eo
    -0.13
    eed
    -0.13
    POSITIVE LOGITS
    adays
    0.19
    oret
    0.17
    fare
    0.15
    oretical
    0.15
    laps
    0.15
    erialize
    0.14
    budget
    0.14
    atre
    0.14
    REA
    0.14
    sez
    0.14
    Act Density 0.191%

    No Known Activations