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

    Neuronpedia

    INDEX
    Explanations

    negative numerical values and mathematical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clar
    -0.14
     GPLv
    -0.14
    adle
    -0.14
     pale
    -0.14
     maks
    -0.13
    elize
    -0.13
    andin
    -0.13
    otland
    -0.13
    _IOC
    -0.13
    Ñijм
    -0.13
    POSITIVE LOGITS
    ispens
    0.15
    ails
    0.14
    ovich
    0.14
    ër
    0.14
     Bis
    0.13
    NECT
    0.13
    /+
    0.13
    éīĦ
    0.13
    urt
    0.13
    ardo
    0.13
    Act Density 0.055%

    No Known Activations