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

    Neuronpedia

    INDEX
    Explanations

    instances of lists or list formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okit
    -0.15
     Lah
    -0.14
    ksen
    -0.14
    adro
    -0.14
    encies
    -0.14
    rade
    -0.13
    vfs
    -0.13
    inges
    -0.13
    orno
    -0.13
    adar
    -0.13
    POSITIVE LOGITS
    aura
    0.17
    ow
    0.15
    项
    0.15
    tica
    0.15
    -unstyled
    0.15
    áct
    0.15
    æľ¬å½ĵãģ«
    0.14
    rong
    0.14
    ocaly
    0.14
     LENG
    0.14
    Act Density 0.033%

    No Known Activations