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

    Neuronpedia

    INDEX
    Explanations

    references to testing frameworks and their processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afil
    -0.15
    ÃĤ
    -0.14
    ...
    -0.14
    ummings
    -0.14
     ...
    -0.14
    ekim
    -0.13
    ãĢĤæľ¬
    -0.13
    lider
    -0.13
    ......
    -0.13
    ylon
    -0.12
    POSITIVE LOGITS
    estli
    0.12
     ìĹŃìĭľ
    0.12
    NSNotification
    0.12
    _excerpt
    0.12
     CreateMap
    0.12
     acomp
    0.12
     ``(
    0.11
    ô
    0.11
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.11
     |[
    0.11
    Act Density 0.389%

    No Known Activations