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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating large quantities or numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /stretch
    -0.14
    iêu
    -0.14
    گاÙĨÛĮ
    -0.14
     Horton
    -0.14
     пÑĥ
    -0.14
    ildiÄŁi
    -0.14
    LOT
    -0.14
    کارÛĮ
    -0.13
    fort
    -0.13
    515
    -0.13
    POSITIVE LOGITS
    ajs
    0.16
    oba
    0.15
     dozen
    0.15
    ocom
    0.14
    imulation
    0.14
    ecz
    0.14
    Äįe
    0.14
    opher
    0.14
     hundreds
    0.14
     thousands
    0.14
    Act Density 0.115%

    No Known Activations