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

    Neuronpedia

    INDEX
    Explanations

    references to software or device settings

    oai_token-act-pair · gpt-3.5-turbo

    references to settings in software or devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ston
    -0.78
    女
    -0.74
    RAY
    -0.70
    teness
    -0.67
    ITNESS
    -0.66
    RECT
    -0.66
    ŃĶ
    -0.65
    iterator
    -0.64
    moving
    -0.63
    ilee
    -0.63
    POSITIVE LOGITS
     settings
    1.13
     Settings
    0.97
    settings
    0.96
    ettings
    0.84
    creen
    0.81
    Settings
    0.78
    imen
    0.76
     configurations
    0.74
    utterstock
    0.74
     Preferences
    0.74
    Act Density 0.010%

    No Known Activations