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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "recognize" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âgées
    -0.74
    fvar
    -0.74
    espère
    -0.72
     délib
    -0.63
    Sortie
    -0.62
     án
    -0.61
     perek
    -0.61
    kuuta
    -0.61
    ंदीखरीदारी
    -0.61
     étions
    -0.60
    POSITIVE LOGITS
     recognise
    1.55
     recognize
    1.54
     recognition
    1.53
     recogni
    1.50
     recognised
    1.50
     recognized
    1.48
     RECOGN
    1.45
     recognizes
    1.43
     recognizing
    1.42
     recognises
    1.42
    Act Density 0.139%

    No Known Activations