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

    Neuronpedia

    INDEX
    Explanations

    unique identifiers or special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.21
    Âł
    -0.20
     '
    -0.19
     âĢ¦↵↵
    -0.17
    ï¼ļ"
    -0.17
     "'
    -0.17
     "[
    -0.16
     ‘
    -0.16
    ÂłD
    -0.16
     “
    -0.16
    POSITIVE LOGITS
     Arizona
    0.65
    Arizona
    0.56
     Tucson
    0.52
     AZ
    0.51
    AZ
    0.43
     Phoenix
    0.40
    Phoenix
    0.37
     Az
    0.34
     az
    0.34
    ucson
    0.33
    Act Density 0.004%

    No Known Activations