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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "Without" that indicate a conditional statement or a scenario where something is lacking

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    late
    -0.84
     Appears
    -0.77
    ortment
    -0.76
    des
    -0.73
    ounce
    -0.72
    lator
    -0.71
    æ©
    -0.69
    dry
    -0.68
    chet
    -0.67
    eared
    -0.67
    POSITIVE LOGITS
     exception
    1.20
     doubt
    1.12
     hesitation
    1.07
     mentioning
    1.05
     knowing
    1.05
     compromising
    0.90
     specifying
    0.88
     adequate
    0.87
     exaggeration
    0.87
     recourse
    0.85
    Act Density 0.033%

    No Known Activations