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

    Neuronpedia

    INDEX
    Explanations

    terms related to control and limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    @$
    -0.17
    obe
    -0.16
    akis
    -0.15
    stones
    -0.14
    ahoma
    -0.14
    ston
    -0.14
    plode
    -0.14
    ertino
    -0.14
    atorial
    -0.13
    :title
    -0.13
    POSITIVE LOGITS
     sim
    0.14
    _VISIBLE
    0.14
    eed
    0.14
    rance
    0.14
    ep
    0.14
    ä½ı
    0.14
    ĶåĽŀ
    0.13
     ideal
    0.13
     Serialized
    0.13
     Bilder
    0.13
    Act Density 0.012%

    No Known Activations