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

    Neuronpedia

    INDEX
    Explanations

    the character "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    significant numerical values or quantifiable metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GP
    -0.85
     Mosque
    -0.85
     Olympic
    -0.85
     Replay
    -0.83
     AP
    -0.83
     Campaign
    -0.81
     Font
    -0.80
     Temple
    -0.80
     Robot
    -0.80
     Brotherhood
    -0.80
    POSITIVE LOGITS
    then
    1.54
    another
    1.53
    why
    1.52
    these
    1.48
    reply
    1.47
    they
    1.45
    please
    1.44
    someone
    1.44
    there
    1.43
    click
    1.43
    Act Density 0.546%

    No Known Activations