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

    Neuronpedia

    INDEX
    Explanations

    non-standard or unconventional spelling patterns and character sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .setDefault
    -0.15
    eny
    -0.14
    uild
    -0.14
    RESS
    -0.14
    tight
    -0.14
    Äįit
    -0.14
    uze
    -0.14
     wedge
    -0.14
    437
    -0.14
    太éĥİ
    -0.14
    POSITIVE LOGITS
    abwe
    0.17
     PUS
    0.16
    Breadcrumb
    0.15
    riend
    0.15
    uese
    0.15
     лÑĮ
    0.14
     Lod
    0.14
    ãĥ¼ãĥ©
    0.14
    ewire
    0.14
    erville
    0.14
    Act Density 0.070%

    No Known Activations