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

    Neuronpedia

    INDEX
    Explanations

    patterns and sequences of numerical figures, specifically related to data representation or citation figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -2.19
    majánló
    -2.02
    <unused74>
    -2.02
    [@BOS@]
    -2.00
    <unused41>
    -2.00
    <unused14>
    -2.00
    <unused28>
    -2.00
    <unused23>
    -2.00
    <unused3>
    -2.00
    <unused8>
    -2.00
    POSITIVE LOGITS
    1
    2.42
    2
    1.64
    3
    1.59
    5
    1.53
    4
    1.48
    6
    1.45
    7
    1.45
    9
    1.43
    0
    1.39
    8
    1.36
    Act Density 1.914%

    No Known Activations