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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software or system settings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    kees
    -0.97
    flies
    -0.87
    zz
    -0.82
     Shroud
    -0.78
     Kush
    -0.76
     Gamble
    -0.73
    Kn
    -0.73
    Hack
    -0.72
    Cu
    -0.71
     cloves
    -0.71
    POSITIVE LOGITS
     peripheral
    0.90
     conventional
    0.90
    ventional
    0.85
     genuine
    0.84
     Regional
    0.84
    english
    0.83
     supra
    0.83
     holistic
    0.82
     universal
    0.82
     collegiate
    0.81
    Act Density 0.345%

    No Known Activations