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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to mathematical expressions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hubb
    -0.13
    ½Ķ
    -0.13
    mits
    -0.13
     opak
    -0.13
    ãĥ©ãĤ¯
    -0.13
    -inverse
    -0.13
    /upload
    -0.13
    ego
    -0.13
    alta
    -0.12
     spou
    -0.12
    POSITIVE LOGITS
     such
    0.15
     only
    0.15
     Such
    0.14
     we
    0.14
    aaS
    0.14
    ottie
    0.14
     for
    0.14
     care
    0.14
    ighb
    0.14
     practical
    0.14
    Act Density 0.386%

    No Known Activations