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

    Neuronpedia

    INDEX
    Explanations

    references to various types of models used in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chter
    -0.14
    atum
    -0.14
    entina
    -0.14
    vant
    -0.14
    ugen
    -0.14
    meal
    -0.13
    layan
    -0.13
    448
    -0.13
    _RW
    -0.13
    ñana
    -0.13
    POSITIVE LOGITS
    iken
    0.17
    led
    0.16
    泡
    0.15
    emento
    0.14
    kaar
    0.14
    isel
    0.14
    gie
    0.13
    les
    0.13
    UnderTest
    0.13
    ias
    0.13
    Act Density 0.024%

    No Known Activations