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

    Neuronpedia

    INDEX
    Explanations

    characters or symbols used for punctuation or formatting within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cube
    -0.15
    JECTION
    -0.14
    evice
    -0.14
    xCD
    -0.14
    coal
    -0.14
    _ENABLED
    -0.14
     Mond
    -0.13
     Ezek
    -0.13
     Jerseys
    -0.13
    voir
    -0.13
    POSITIVE LOGITS
    icho
    0.16
    onso
    0.16
    437
    0.16
    zano
    0.15
    engu
    0.15
    contri
    0.15
    riere
    0.15
    ayne
    0.15
    umbing
    0.14
    éļł
    0.14
    Act Density 0.005%

    No Known Activations