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

    Neuronpedia

    INDEX
    Explanations

    punctuations and symbols used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ings
    -0.15
    odi
    -0.14
    -↵↵
    -0.14
    raj
    -0.14
    ruk
    -0.14
    Ñĥд
    -0.13
    ley
    -0.13
    lett
    -0.13
     respective
    -0.13
    ons
    -0.13
    POSITIVE LOGITS
    s
    0.26
    enler
    0.19
    Ùĩ
    0.19
    al
    0.19
    y
    0.18
    sian
    0.18
    à¸Ļ
    0.17
    à¸Ħ
    0.16
    ÏĤ
    0.16
    sip
    0.16
    Act Density 0.283%

    No Known Activations