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

    Neuronpedia

    INDEX
    Explanations

    references to standards or norms in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Loren
    -0.15
    olu
    -0.14
    ucc
    -0.13
    itto
    -0.13
    udi
    -0.13
     CascadeType
    -0.13
     instead
    -0.13
    alone
    -0.13
     pis
    -0.13
     involved
    -0.13
    POSITIVE LOGITS
     others
    0.17
    Ïģιν
    0.15
    nier
    0.15
    velle
    0.15
    VIOUS
    0.15
    others
    0.15
    ¶Į
    0.15
     ones
    0.15
    à¸Ļà¸ģ
    0.15
     Ulus
    0.14
    Act Density 0.079%

    No Known Activations