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

    Neuronpedia

    INDEX
    Explanations

    occurrences of certain high-frequency or significant conjunctions and prepositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»ĵ
    -0.17
    amps
    -0.15
     block
    -0.15
    lik
    -0.15
    favor
    -0.14
     favor
    -0.14
    astle
    -0.14
    ÑĢава
    -0.14
    ague
    -0.14
    足
    -0.13
    POSITIVE LOGITS
    pairs
    0.17
    ayo
    0.17
    primitive
    0.16
    ázal
    0.16
    erece
    0.15
    uition
    0.15
    Pairs
    0.15
    à¸Ńà¹Ģร
    0.15
    SupportedContent
    0.15
    .Unicode
    0.15
    Act Density 0.019%

    No Known Activations