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

    Neuronpedia

    INDEX
    Explanations

    hyphenated phrases

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiment or criticism in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dickinson
    -0.80
     Arabian
    -0.75
     Confederation
    -0.69
    ļéĨĴ
    -0.67
     eternity
    -0.66
     constellation
    -0.65
     Wiz
    -0.65
     dressing
    -0.63
     Compass
    -0.63
     helm
    -0.62
    POSITIVE LOGITS
    sized
    1.18
    based
    1.14
    eyed
    1.06
    shaped
    1.04
    minded
    1.01
    level
    0.99
    tailed
    0.98
    sided
    0.97
    quartered
    0.96
    scale
    0.95
    Act Density 0.256%

    No Known Activations