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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating requests for comments or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cu
    -0.17
     Dez
    -0.14
    ´Ī
    -0.14
    subs
    -0.14
    è¼ī
    -0.14
     res
    -0.14
    .BLL
    -0.14
    extensions
    -0.13
    éc
    -0.13
    ycz
    -0.13
    POSITIVE LOGITS
    леÑĢ
    0.17
    orry
    0.15
    ãĤıãģĽ
    0.15
    LEN
    0.14
    hei
    0.14
    ibo
    0.14
    iddle
    0.14
    fak
    0.13
     Mour
    0.13
    loor
    0.13
    Act Density 0.007%

    No Known Activations