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

    Neuronpedia

    INDEX
    Explanations

    colons and various types of separators in code or markup contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulan
    -0.16
    urt
    -0.16
    obot
    -0.15
    eza
    -0.15
    ersh
    -0.15
    ree
    -0.14
    uhn
    -0.14
    aryana
    -0.14
    urtle
    -0.14
    wers
    -0.13
    POSITIVE LOGITS
    ubic
    0.17
    tings
    0.15
    ন
    0.14
    aload
    0.14
    ossed
    0.14
    ůst
    0.14
    ิร
    0.14
    -ground
    0.14
    iban
    0.13
    _TOOL
    0.13
    Act Density 0.032%

    No Known Activations