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

    Neuronpedia

    INDEX
    Explanations

    a specific pattern of characters 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of code or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     acceler
    -0.77
     Kingston
    -0.73
     ambassadors
    -0.69
     severed
    -0.68
     inward
    -0.68
     starved
    -0.67
     accelerated
    -0.65
     Tart
    -0.64
     slam
    -0.63
     vortex
    -0.63
    POSITIVE LOGITS
    Trivia
    1.17
    âĵĺ
    1.09
    ãĥ¯ãĥ³
    1.09
    References
    1.06
    ////////////////
    1.02
    FINEST
    1.01
    --------------------------------------------------------
    1.01
    ////////
    1.00
    ãĤ´
    0.97
    è¦ļéĨĴ
    0.97
    Act Density 0.174%

    No Known Activations