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

    Neuronpedia

    INDEX
    Explanations

    references to estimates or estimates of risk in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Chooser
    -0.16
    ocr
    -0.14
    ai
    -0.14
     fixed
    -0.14
    .ContentType
    -0.13
     Jahres
    -0.13
     Sanford
    -0.13
    جÙĦ
    -0.13
    -%
    -0.13
     revival
    -0.13
    POSITIVE LOGITS
     cautioned
    0.21
     caution
    0.21
    Pending
    0.19
     pending
    0.19
     Cave
    0.18
    pending
    0.18
     Pending
    0.18
    ãģ¾ãģł
    0.18
     still
    0.18
     cave
    0.17
    Act Density 0.124%

    No Known Activations