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

    Neuronpedia

    INDEX
    Explanations

    references to adjectives and their functions in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĪ¶
    -0.15
    اÙĪرÛĮ
    -0.15
    ura
    -0.15
    PPP
    -0.15
    eyer
    -0.15
    aan
    -0.15
    oti
    -0.14
    tures
    -0.13
    ling
    -0.13
     scaleY
    -0.13
    POSITIVE LOGITS
    ĨĴ
    0.15
    omu
    0.14
    OfClass
    0.14
    nett
    0.14
     Cliff
    0.14
     Ris
    0.13
    aines
    0.13
    izon
    0.13
    647
    0.13
    wnd
    0.13
    Act Density 0.020%

    No Known Activations