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

    Neuronpedia

    INDEX
    Explanations

    instances of text indicating updates or modifications to content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umont
    -0.07
    }->
    -0.07
    _alias
    -0.07
    logen
    -0.06
    aly
    -0.06
    atti
    -0.06
    ach
    -0.06
    enta
    -0.06
    æĬ¬
    -0.06
    igt
    -0.06
    POSITIVE LOGITS
     later
    0.07
    entar
    0.06
    ãģıãĤĵ
    0.06
    later
    0.06
    ãĥ¼ãĥĦ
    0.06
     Mic
    0.06
    oser
    0.06
    lesi
    0.06
    Ïģγ
    0.06
    yntax
    0.06
    Act Density 0.003%

    No Known Activations