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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific goals or objectives

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate intentions or goals of organizations or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Kings
    -0.63
     References
    -0.60
     Disapp
    -0.60
    nova
    -0.59
     misses
    -0.58
    wine
    -0.57
     Quit
    -0.57
     Transcript
    -0.56
     Tact
    -0.56
    inventoryQuantity
    -0.55
    POSITIVE LOGITS
     mainly
    0.86
     principally
    0.83
     primarily
    0.83
    rils
    0.81
    ciplinary
    0.78
     broadly
    0.77
     chiefly
    0.76
    earchers
    0.74
     specifically
    0.72
     combating
    0.71
    Act Density 0.211%

    No Known Activations