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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific terms related to organization or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Falls
    -0.15
     Associates
    -0.15
    .defaults
    -0.15
    票
    -0.14
    stem
    -0.14
     Steph
    -0.13
    utorials
    -0.13
    oner
    -0.13
     Kerr
    -0.13
    ingham
    -0.13
    POSITIVE LOGITS
    ffen
    0.18
     nackte
    0.16
    GuidId
    0.16
    NullOr
    0.15
    uptime
    0.15
     Highlander
    0.14
    UCE
    0.14
    ichten
    0.14
    алÑĮ
    0.14
    ãĤŃãĥ¥
    0.14
    Act Density 0.001%

    No Known Activations