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

    Neuronpedia

    INDEX
    Explanations

    terms indicating mathematical or structural relationships involving constraints and populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     &___
    -0.65
    enciaga
    -0.64
    postIndex
    -0.63
    drawSprites
    -0.61
    Personensuche
    -0.61
    endphp
    -0.61
    awtextra
    -0.61
     peric
    -0.61
    MessageTagHelper
    -0.61
    StoreMessageInfo
    -0.60
    POSITIVE LOGITS
     наоборот
    0.63
     justru
    0.54
     hingegen
    0.53
     less
    0.52
     more
    0.48
     not
    0.47
    wikia
    0.46
     invece
    0.46
     wel
    0.45
    SharedCtor
    0.45
    Act Density 0.886%

    No Known Activations