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

    Neuronpedia

    INDEX
    Explanations

    queries or prompts for discussions about various topics

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "What about" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gallery
    -0.71
    rang
    -0.69
    Lens
    -0.69
     Peaks
    -0.67
    KC
    -0.67
    ¯¯¯¯¯¯¯¯
    -0.67
     Writ
    -0.67
    Writer
    -0.66
    UES
    -0.65
    ocaly
    -0.64
    POSITIVE LOGITS
     halfway
    0.78
     how
    0.70
     calib
    0.69
     respecting
    0.68
    lihood
    0.66
     reforming
    0.66
     whether
    0.65
     fairness
    0.64
     repealing
    0.64
    roying
    0.63
    Act Density 0.147%

    No Known Activations