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

    Neuronpedia

    INDEX
    Explanations

    repeated character sequences or special characters in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adius
    -0.15
     Michigan
    -0.15
     Wichita
    -0.15
    regon
    -0.15
    ä»Ķ
    -0.14
     Hoover
    -0.14
     Midwest
    -0.14
     Illinois
    -0.14
     nắm
    -0.14
     Wisconsin
    -0.14
    POSITIVE LOGITS
     Jamaica
    0.34
     Jama
    0.31
     programmes
    0.26
     Caribbean
    0.26
     programme
    0.24
     Kingston
    0.23
     Trinidad
    0.23
     Sport
    0.23
     Ghana
    0.23
     Programme
    0.23
    Act Density 0.004%

    No Known Activations