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

    Neuronpedia

    INDEX
    Explanations

    positive qualities or attributes about something

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating positive quality or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.71
    emb
    -0.71
    isSpecialOrderable
    -0.70
    let
    -0.70
    ":[
    -0.69
    rophe
    -0.69
    emonium
    -0.69
    Clar
    -0.68
    uthor
    -0.65
    lets
    -0.65
    POSITIVE LOGITS
     grades
    1.12
     quality
    1.07
     intentions
    1.07
     results
    1.06
     luck
    1.05
     odds
    1.04
     outcomes
    1.01
     fundamentals
    0.99
     ratios
    0.98
     amounts
    0.94
    Act Density 0.132%

    No Known Activations