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

    Neuronpedia

    INDEX
    Explanations

    markers of negation or rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.66
    NUMX
    -0.64
    \{\\
    -0.62
     ujednoznacz
    -0.60
    homonymie
    -0.59
     المعيارى
    -0.55
    ScopeManager
    -0.54
    ifikationer
    -0.54
    WebServlet
    -0.53
     AspNetCore
    -0.52
    POSITIVE LOGITS
    IContainer
    0.68
    Jîn
    0.63
     ſta
    0.59
    ieties
    0.56
    通販
    0.55
     purpoſe
    0.55
     sirens
    0.53
     himſelf
    0.53
     Głów
    0.52
     neceff
    0.52
    Act Density 0.181%

    No Known Activations