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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technical aspects or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ktop
    -0.80
    stellar
    -0.79
    velt
    -0.78
    lain
    -0.77
    hyde
    -0.74
    lein
    -0.74
    KI
    -0.70
     Twain
    -0.70
     Sheen
    -0.70
    winner
    -0.65
    POSITIVE LOGITS
     specifications
    0.96
     Specifications
    0.91
     jargon
    0.89
     glitches
    0.86
     difficulties
    0.85
     specs
    0.85
    iencies
    0.84
     proficiency
    0.83
     prowess
    0.82
     considerations
    0.81
    Act Density 0.020%

    No Known Activations