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

    Neuronpedia

    INDEX
    Explanations

    concepts related to transformation or change in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÇIJ
    -0.15
    "group
    -0.15
    ãĥ¼ãĥī
    -0.15
    ebo
    -0.14
    idot
    -0.14
    routeProvider
    -0.14
    ãģĿãģĨãģª
    -0.14
    íģ
    -0.14
    toPromise
    -0.13
    ijken
    -0.13
    POSITIVE LOGITS
     pedig
    0.18
     коÑĤоÑĢÑĭÑħ
    0.17
     has
    0.17
     is
    0.16
     коÑĤоÑĢого
    0.15
     must
    0.15
     Uncategorized
    0.15
     can
    0.15
     becomes
    0.15
     became
    0.15
    Act Density 1.162%

    No Known Activations