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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and symbols associated with formal proofs and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enis
    -0.17
    ategory
    -0.15
    altung
    -0.14
    lož
    -0.14
    apixel
    -0.14
    gcd
    -0.14
    erken
    -0.14
    ROUGH
    -0.14
    ابÛĮ
    -0.13
    _NEED
    -0.13
    POSITIVE LOGITS
    ones
    0.16
    arten
    0.15
    opi
    0.15
    chester
    0.15
     Ridley
    0.14
    arto
    0.14
    วรร
    0.14
    oster
    0.14
     Duo
    0.14
    ollar
    0.14
    Act Density 0.024%

    No Known Activations