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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters used in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abol
    -0.15
    cess
    -0.15
    lop
    -0.14
    iversal
    -0.14
     humans
    -0.13
     catch
    -0.13
    .coord
    -0.13
    873
    -0.13
    leston
    -0.13
    ekk
    -0.13
    POSITIVE LOGITS
    auf
    0.16
    bon
    0.16
    PTION
    0.14
    ãĥ©ãĤ¹
    0.14
    иÑĨ
    0.14
    @nate
    0.14
    icz
    0.14
     {}).
    0.14
    æĮº
    0.13
    otes
    0.13
    Act Density 0.139%

    No Known Activations