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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters that repeat or appear frequently

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    алÑĥ
    -0.18
    aku
    -0.17
     Middleton
    -0.17
    ODO
    -0.16
    roud
    -0.16
    atra
    -0.15
    kest
    -0.15
    bler
    -0.15
    Margins
    -0.15
    croft
    -0.15
    POSITIVE LOGITS
    static
    0.17
     Har
    0.17
     static
    0.17
     har
    0.16
    aret
    0.16
     LENG
    0.16
     statically
    0.15
    97
    0.15
     Moy
    0.15
    ussian
    0.15
    Act Density 0.003%

    No Known Activations