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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting elements commonly found in academic writing or research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apt
    -0.16
    '].$
    -0.15
    _HINT
    -0.15
    ãģ¡
    -0.14
    afil
    -0.14
    BackColor
    -0.14
    arna
    -0.14
    503
    -0.14
    /fw
    -0.14
    alar
    -0.13
    POSITIVE LOGITS
    onal
    0.16
    avy
    0.15
    mÄĽ
    0.15
    e
    0.15
     o
    0.15
    oard
    0.15
     ÑĪÑĤ
    0.14
    uml
    0.14
    onest
    0.13
    o
    0.13
    Act Density 0.019%

    No Known Activations