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

    Neuronpedia

    INDEX
    Explanations

    words that indicate large quantities or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iqueta
    -0.16
    ayas
    -0.16
    amble
    -0.15
    اÙħبر
    -0.14
    ailer
    -0.14
    raig
    -0.14
     Marketable
    -0.14
    ãĥĭãĤ¢
    -0.14
    batis
    -0.14
    %p
    -0.13
    POSITIVE LOGITS
     upon
    0.44
    upon
    0.37
     Upon
    0.34
    Upon
    0.33
    -strong
    0.22
    -fold
    0.18
    /th
    0.18
    -long
    0.17
    /groups
    0.17
    fold
    0.17
    Act Density 0.022%

    No Known Activations