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

    Neuronpedia

    INDEX
    Explanations

    complex themes and interactions between distinct elements or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Icons
    -0.15
    unga
    -0.14
    ì©
    -0.13
    è¨Ģ
    -0.13
     gastro
    -0.13
    ãĥ©ãĥ¼
    -0.13
     "'.
    -0.13
    .axes
    -0.13
     اÙĦرÙĬاض
    -0.13
     dokon
    -0.13
    POSITIVE LOGITS
    ermann
    0.20
    heed
    0.15
    ANGO
    0.15
     meiden
    0.15
    ibri
    0.15
    ì´
    0.15
    -chevron
    0.15
    edom
    0.14
    cone
    0.14
    edm
    0.14
    Act Density 0.156%

    No Known Activations