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

    Neuronpedia

    INDEX
    Explanations

    steps or instructions related to using technology

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     flour
    -0.83
     purported
    -0.80
     leaps
    -0.78
     oft
    -0.74
     sprawling
    -0.73
     ranc
    -0.73
     slaying
    -0.70
     caric
    -0.69
     flourishing
    -0.69
     lesbians
    -0.68
    POSITIVE LOGITS
    Apply
    1.04
    Exit
    1.03
    submit
    1.02
    AUT
    1.02
    Default
    1.01
    Display
    1.00
    default
    0.98
    RET
    0.98
    Advanced
    0.97
    Create
    0.96
    Act Density 0.094%

    No Known Activations