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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers that are arranged in a specific format

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     shenan
    -2.11
     impra
    -2.04
     accla
    -2.02
     reluct
    -2.02
     sophistic
    -2.01
     indestru
    -2.00
     pamph
    -1.99
     philanth
    -1.98
     disagre
    -1.98
     unspeak
    -1.91
    POSITIVE LOGITS
     DRAWINGS
    0.70
    0
    0.69
    PREFERRED
    0.64
     requerimientos
    0.61
    cnica
    0.60
     renovables
    0.60
    ribune
    0.59
    fill
    0.57
     sentimientos
    0.56
    ടു
    0.56
    Act Density 0.158%

    No Known Activations