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

    Neuronpedia

    INDEX
    Explanations

    negative or contradictory statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĪ¸
    -0.17
    jej
    -0.15
    ]={↵
    -0.15
    ozilla
    -0.15
    jest
    -0.14
    _mapped
    -0.14
    éĢł
    -0.14
    opher
    -0.14
    strap
    -0.14
    quo
    -0.14
    POSITIVE LOGITS
     nor
    0.22
     not
    0.21
     не
    0.19
     không
    0.19
     नह
    0.18
     niet
    0.18
     tidak
    0.18
     neither
    0.17
     nicht
    0.16
     geen
    0.16
    Act Density 0.035%

    No Known Activations