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

    Neuronpedia

    INDEX
    Explanations

    special character sequences that likely represent formatting or encoding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ia
    -0.19
     j
    -0.16
    kla
    -0.16
     MLA
    -0.15
    akk
    -0.14
    ongyang
    -0.14
    alem
    -0.14
    ENA
    -0.14
     Starbucks
    -0.14
     aug
    -0.13
    POSITIVE LOGITS
     Mos
    0.28
    Mos
    0.21
     bomber
    0.18
     bombers
    0.17
     Coastal
    0.16
     Bom
    0.16
     mos
    0.16
    ãĥ©ãĥĥãĤ¯
    0.16
    /os
    0.15
    moz
    0.15
    Act Density 0.002%

    No Known Activations