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

    Neuronpedia

    INDEX
    Explanations

    references to historical events or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wanna
    -0.16
    à¸Ļà¸Ļ
    -0.15
     Zuk
    -0.15
    bard
    -0.15
     telev
    -0.15
    ırak
    -0.14
    @js
    -0.14
     Sadd
    -0.14
    opsis
    -0.14
    ause
    -0.14
    POSITIVE LOGITS
    188
    0.19
     liberalism
    0.17
    191
    0.16
    187
    0.16
     censor
    0.15
     provisional
    0.15
     pedestal
    0.15
     Mason
    0.15
     liberals
    0.15
    189
    0.15
    Act Density 0.062%

    No Known Activations