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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     replies
    -0.71
    felt
    -0.68
    quickShipAvailable
    -0.63
    ortun
    -0.62
    mails
    -0.62
    abiding
    -0.62
     calculations
    -0.62
    ãĤ¦ãĤ¹
    -0.62
    cases
    -0.62
    stories
    -0.61
    POSITIVE LOGITS
     relocate
    1.28
     legalize
    1.24
     postpone
    1.21
     introduce
    1.19
     evacuate
    1.18
     marry
    1.15
     eliminate
    1.14
     create
    1.13
     bring
    1.13
     abolish
    1.13
    Act Density 0.144%

    No Known Activations