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

    Neuronpedia

    INDEX
    Explanations

    unusual character sequences and punctuation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anz
    -0.16
    lander
    -0.16
    arend
    -0.16
    ect
    -0.16
     風
    -0.15
     ÑĢавно
    -0.15
    anky
    -0.15
    ects
    -0.15
    veloper
    -0.15
    ewolf
    -0.14
    POSITIVE LOGITS
     Leban
    0.17
    avenport
    0.16
    clarsimp
    0.14
    /vendor
    0.13
    ignum
    0.13
    itom
    0.13
    _IOC
    0.13
     Wilkinson
    0.13
    ãĥ¼ãĥķ
    0.13
    wort
    0.13
    Act Density 0.040%

    No Known Activations