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

    Neuronpedia

    INDEX
    Explanations

    words related to side effects and alternative uses of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ìĬ¤íĬ¸
    -0.14
    OperationException
    -0.14
    estroy
    -0.14
    Ctl
    -0.14
    ç¢
    -0.14
    _MSK
    -0.14
    .MixedReality
    -0.13
    ropolitan
    -0.13
    furt
    -0.13
     already
    -0.13
    POSITIVE LOGITS
    rics
    0.15
     Beyond
    0.14
    ification
    0.14
    leet
    0.14
    058
    0.13
    ahn
    0.13
    oco
    0.13
    оги
    0.13
    urn
    0.13
    ail
    0.13
    Act Density 0.047%

    No Known Activations