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

    Neuronpedia

    INDEX
    Explanations

    quantitative measures related to demographics and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amu
    -0.15
     Anton
    -0.14
     Da
    -0.14
    ields
    -0.14
    ampus
    -0.14
    ady
    -0.14
     Disclosure
    -0.14
    ÅĻen
    -0.14
     Dos
    -0.14
     dosage
    -0.14
    POSITIVE LOGITS
    érica
    0.16
    ÑĤÑĮ
    0.16
    åĿĬ
    0.16
    _VOL
    0.15
    ضÙĪ
    0.15
    olum
    0.14
    меÑĩ
    0.14
    adele
    0.14
    éric
    0.14
    iez
    0.14
    Act Density 0.296%

    No Known Activations