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

    Neuronpedia

    INDEX
    Explanations

    references to enhancements or upgrades in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ify
    -0.16
    lor
    -0.15
    ados
    -0.15
     Pornhub
    -0.15
    ieder
    -0.15
    iven
    -0.14
    ified
    -0.14
    lom
    -0.14
    ee
    -0.14
    ouis
    -0.14
    POSITIVE LOGITS
    ODO
    0.16
    049
    0.15
    upal
    0.15
    hof
    0.14
    phis
    0.14
    Æ°u
    0.14
    rapped
    0.14
    :\/\/
    0.14
    _callable
    0.13
    βε
    0.13
    Act Density 0.019%

    No Known Activations