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

    Neuronpedia

    INDEX
    Explanations

    phrases related to debate participation and eligibility criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avn
    -0.16
     arac
    -0.15
    abase
    -0.14
    onio
    -0.14
     Horse
    -0.14
    ellt
    -0.13
    /File
    -0.13
    ABB
    -0.13
    ÙĬÙĨÙĩ
    -0.13
    ilot
    -0.13
    POSITIVE LOGITS
     division
    0.29
     Open
    0.27
     divisions
    0.27
    division
    0.26
     open
    0.24
     category
    0.24
     Division
    0.23
     age
    0.22
     senior
    0.21
     Senior
    0.21
    Act Density 0.129%

    No Known Activations