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

    Neuronpedia

    INDEX
    Explanations

    comparative statements regarding preferences and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Heller
    -0.18
    ucc
    -0.16
    sson
    -0.16
    azon
    -0.15
    thood
    -0.15
    ระ
    -0.14
    ?url
    -0.14
    mutable
    -0.14
    ÛĮاÙĨ
    -0.14
    addock
    -0.14
    POSITIVE LOGITS
    .vertx
    0.15
    inee
    0.15
    apes
    0.14
    essen
    0.14
    amik
    0.14
    ÑĥмÑĥ
    0.14
    iene
    0.14
    administrator
    0.14
     sÄĥ
    0.13
    abee
    0.13
    Act Density 0.157%

    No Known Activations