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

    Neuronpedia

    INDEX
    Explanations

    terms indicating uncertainty or comparisons involving "quite" and "slightly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ald
    -0.18
    arde
    -0.18
    lin
    -0.15
    itel
    -0.15
    454
    -0.15
    tera
    -0.15
    VERBOSE
    -0.14
    ologne
    -0.14
     konkrét
    -0.14
    adir
    -0.14
    POSITIVE LOGITS
    iÃŃ
    0.18
    имв
    0.16
    ëħĦëıĦ
    0.15
     slightly
    0.15
    edImage
    0.14
     beforeSend
    0.14
    -ÑĤаки
    0.14
    empo
    0.14
     version
    0.14
    onica
    0.14
    Act Density 0.065%

    No Known Activations