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

    Neuronpedia

    INDEX
    Explanations

    references to articles or posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unga
    -0.14
     causes
    -0.14
    ields
    -0.14
     produces
    -0.13
    ighest
    -0.13
     becomes
    -0.13
    usta
    -0.13
    eÅŁ
    -0.13
    ustain
    -0.13
    undo
    -0.13
    POSITIVE LOGITS
     discusses
    0.21
     deals
    0.21
     summarize
    0.20
     contain
    0.20
     concerns
    0.19
     discuss
    0.19
     summar
    0.19
     pert
    0.19
     hopefully
    0.19
     intentionally
    0.19
    Act Density 0.195%

    No Known Activations