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

    Neuronpedia

    INDEX
    Explanations

    frequent occurrences of the word "the" and other functional words that help define context in written text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertz
    -0.17
    аÑĤив
    -0.16
    iem
    -0.16
    ilo
    -0.15
    acion
    -0.15
    á»Ļc
    -0.14
    ackbar
    -0.14
    aturity
    -0.14
    iliz
    -0.14
    azio
    -0.13
    POSITIVE LOGITS
     name
    0.17
    ens
    0.15
    name
    0.15
    ONA
    0.14
    wig
    0.14
    aise
    0.14
    -name
    0.14
    than
    0.14
     Nine
    0.14
    айд
    0.14
    Act Density 0.002%

    No Known Activations