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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific official documents or announcements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character sequence 'âĢ'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scatter
    -0.77
    uliffe
    -0.74
    anwhile
    -0.72
     protective
    -0.70
     Golem
    -0.69
     staggered
    -0.68
     whirlwind
    -0.67
     buggy
    -0.65
     dedication
    -0.65
     proto
    -0.64
    POSITIVE LOGITS
    âĢ
    1.19
    į
    1.03
    âĢķ
    1.02
     âĢº
    1.02
    âĢł
    1.02
    ¹
    1.00
    ĸļ
    0.97
    º
    0.96
    »
    0.93
    ¿
    0.93
    Act Density 0.755%

    No Known Activations