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

    Neuronpedia

    INDEX
    Explanations

    individual digits or numbers in a mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical comparisons involving the number two

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -1.38
    ,:);
    -1.22
     itſelf
    -1.19
     Efq
    -1.13
     ་་
    -1.12
     ſche
    -1.12
     purpoſe
    -1.08
    Personensuche
    -1.06
     ſtate
    -1.05
     himo
    -1.03
    POSITIVE LOGITS
    2
    1.13
    3
    0.92
    4
    0.91
    5
    0.91
    0
    0.89
     two
    0.88
    1
    0.86
    two
    0.76
     Two
    0.75
     T
    0.73
    Act Density 1.009%

    No Known Activations