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

    Neuronpedia

    INDEX
    Explanations

    phrases that imply contrast or opposition

    oai_token-act-pair · gpt-3.5-turbo

    the word "the," indicating a focus on definite articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wash
    -0.73
    boarding
    -0.73
    ifies
    -0.71
    icho
    -0.69
    ify
    -0.68
    vernight
    -0.68
    let
    -0.67
    tackle
    -0.66
    elaide
    -0.66
    ometers
    -0.64
    POSITIVE LOGITS
     possibility
    1.25
     latter
    1.16
     extent
    1.14
     entirety
    1.14
     slightest
    1.13
     aforementioned
    1.09
     notion
    1.06
     complexities
    1.05
     sheer
    1.05
     absence
    1.05
    Act Density 0.775%

    No Known Activations