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

    Neuronpedia

    INDEX
    Explanations

    references to specific research institutions or academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wend
    -0.15
    .AppSettings
    -0.14
    iphone
    -0.14
    ignet
    -0.14
    oÄŁ
    -0.14
    735
    -0.14
    ÏįÏĦε
    -0.14
    ượng
    -0.14
     extras
    -0.13
    icut
    -0.13
    POSITIVE LOGITS
    (Int
    0.21
    quo
    0.20
    ronic
    0.17
    ÅĽÄĩ
    0.17
    ognito
    0.16
     Murdoch
    0.16
    amic
    0.16
    psc
    0.16
    eÅŁit
    0.16
    spell
    0.15
    Act Density 0.204%

    No Known Activations