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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditions or situations that hinge on the fulfillment of certain conditions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ery
    -0.89
    ARC
    -0.83
    sequence
    -0.82
    ulate
    -0.80
    eries
    -0.77
    entry
    -0.76
     0004
    -0.73
    Maker
    -0.71
    ults
    -0.70
    lator
    -0.70
    POSITIVE LOGITS
     otherwise
    1.14
    soever
    1.12
    fy
    0.90
     expressly
    0.86
     indemn
    0.85
    wcsstore
    0.79
     strictly
    0.79
     necessary
    0.78
    agons
    0.77
     personally
    0.76
    Act Density 6.572%

    No Known Activations