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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating types or categories of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cooldown
    -0.14
    alam
    -0.14
    oppable
    -0.14
    elli
    -0.14
    brook
    -0.14
    chn
    -0.13
    orphic
    -0.13
    bes
    -0.13
    ieu
    -0.13
     cogn
    -0.13
    POSITIVE LOGITS
    weise
    0.17
    rome
    0.14
     Provid
    0.14
    olson
    0.14
    osate
    0.14
    tras
    0.13
    awks
    0.13
    rame
    0.13
    richt
    0.13
    nbsp
    0.13
    Act Density 0.046%

    No Known Activations