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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to evaluation and judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzzi
    -0.18
    æµ®
    -0.15
    uggage
    -0.15
    .routing
    -0.15
    IGNAL
    -0.15
    rary
    -0.15
    [url
    -0.14
     tablesp
    -0.14
    aign
    -0.14
    èĮĤ
    -0.14
    POSITIVE LOGITS
     Cummings
    0.15
     mind
    0.14
    ophilia
    0.14
     Pit
    0.14
     пиÑĤ
    0.14
    olin
    0.14
     Mahar
    0.14
    _rat
    0.14
    adors
    0.14
    Į¨
    0.13
    Act Density 0.016%

    No Known Activations