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

    Neuronpedia

    INDEX
    Explanations

    terms related to legality and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undra
    -0.16
    è£ľ
    -0.15
    UST
    -0.14
    ighton
    -0.14
    ÑĤаб
    -0.14
    phan
    -0.13
    istration
    -0.13
    anian
    -0.13
    ieux
    -0.13
    verbatim
    -0.13
    POSITIVE LOGITS
    orno
    0.17
    iment
    0.15
    703
    0.15
    ness
    0.15
    orney
    0.14
    estation
    0.14
    NSURLSession
    0.13
    jd
    0.13
    emente
    0.13
     manner
    0.13
    Act Density 0.007%

    No Known Activations