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

    Neuronpedia

    INDEX
    Explanations

    phrases related to liability and privacy disclaimers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ç½
    -0.15
     Gust
    -0.14
    ÏĢÎŃ
    -0.13
    ousse
    -0.13
    ired
    -0.13
    ako
    -0.13
     hopefully
    -0.13
    iper
    -0.13
     CAB
    -0.13
    909
    -0.13
    POSITIVE LOGITS
     nor
    0.27
     anymore
    0.18
     Nor
    0.17
    nor
    0.17
    Nor
    0.16
    _EL
    0.15
    aat
    0.15
    idia
    0.15
    ardy
    0.15
     Scha
    0.14
    Act Density 0.025%

    No Known Activations