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

    Neuronpedia

    INDEX
    Explanations

    terms related to authorization and permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geld
    -0.15
    wright
    -0.15
    elyn
    -0.14
    ç¯ī
    -0.14
    iet
    -0.14
    ADX
    -0.14
    звиÑĩай
    -0.14
    zc
    -0.14
    asd
    -0.14
    619
    -0.13
    POSITIVE LOGITS
     Ukr
    0.18
    anded
    0.16
    chluss
    0.15
     Dalton
    0.15
    éro
    0.15
    à¹īาà¸ĩ
    0.14
    baugh
    0.14
     Pornhub
    0.14
    ube
    0.14
    fos
    0.14
    Act Density 0.013%

    No Known Activations