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 and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    velt
    -0.83
    stellar
    -0.82
    lain
    -0.76
    ktop
    -0.76
    hyde
    -0.71
    lein
    -0.70
    KI
    -0.69
    juven
    -0.68
     Twain
    -0.67
    winner
    -0.67
    POSITIVE LOGITS
     specifications
    0.98
     jargon
    0.92
     difficulties
    0.89
     glitches
    0.87
     Specifications
    0.87
     specs
    0.87
    iencies
    0.84
    ities
    0.82
     proficiency
    0.82
     aspects
    0.81
    Act Density 0.020%

    No Known Activations