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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to classifications or types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tit
    -0.14
    ãĤ¯ãĥª
    -0.14
    è½½
    -0.13
    /feed
    -0.13
     diss
    -0.13
     fro
    -0.13
     Diss
    -0.13
    /sql
    -0.13
    rish
    -0.13
     TAR
    -0.13
    POSITIVE LOGITS
    amic
    0.17
     Photograph
    0.16
     alm
    0.16
     DialogInterface
    0.15
    uez
    0.15
    onet
    0.15
    HeaderCode
    0.15
    ξι
    0.14
    webtoken
    0.14
    rum
    0.14
    Act Density 0.068%

    No Known Activations