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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    and
    -0.16
     pÅĻiÄįemž
    -0.14
    ivo
    -0.14
     latter
    -0.14
    opard
    -0.13
    riel
    -0.13
    shima
    -0.13
    wards
    -0.12
    archical
    -0.12
    enty
    -0.12
    POSITIVE LOGITS
    noun
    0.21
     Uncategorized
    0.20
     anyone
    0.19
     like
    0.19
     Others
    0.18
     anybody
    0.17
    Inc
    0.17
     Anyone
    0.17
     huh
    0.17
    0.17
    Act Density 0.802%

    No Known Activations