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

    Neuronpedia

    INDEX
    Explanations

    numbers and numerical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    0
    -0.99
    es
    -0.81
    2
    -0.78
    3
    -0.74
    5
    -0.73
    4
    -0.73
    X
    -0.71
    9
    -0.70
    6
    -0.68
    os
    -0.65
    POSITIVE LOGITS
     ſeveral
    1.40
     itſelf
    1.36
     themſelves
    1.36
     purpoſe
    1.34
    ſelves
    1.34
     ſmall
    1.32
    ſelf
    1.32
     himſelf
    1.32
     againſt
    1.30
     reaſon
    1.30
    Act Density 0.092%

    No Known Activations