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

    Neuronpedia

    INDEX
    Explanations

    symbols and specific characters within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     G
    -0.18
     âĢº
    -0.17
     Pr
    -0.17
     R
    -0.15
     âĸº
    -0.15
     L
    -0.15
    -0.15
    910
    -0.14
     ?:
    -0.14
    ÄįÃŃ
    -0.14
    POSITIVE LOGITS
    <T
    0.27
    <B
    0.24
    <A
    0.24
    <P
    0.22
    <D
    0.21
    <H
    0.18
    &A
    0.18
    <
    0.18
    <F
    0.17
    (TR
    0.17
    Act Density 0.010%

    No Known Activations