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

    Neuronpedia

    INDEX
    Explanations

    the concept of "uniqueness" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ©ãĤ¯
    -0.17
    thew
    -0.15
    go
    -0.14
    thought
    -0.14
    chu
    -0.14
    reu
    -0.14
    /on
    -0.14
    agna
    -0.14
    ÑĩаÑĤ
    -0.14
    аÑĢод
    -0.14
    POSITIVE LOGITS
    ities
    0.20
    ually
    0.19
    eted
    0.19
     blend
    0.17
    eting
    0.17
    ively
    0.16
    istically
    0.16
    ely
    0.15
    857
    0.15
    quam
    0.15
    Act Density 0.024%

    No Known Activations