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

    Neuronpedia

    INDEX
    Explanations

    negative language related to criticism

    oai_token-act-pair · gpt-3.5-turbo

    negative evaluations of situations or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )."
    -1.09
    .")
    -0.86
    ]."
    -0.81
    .""
    -0.76
    ").
    -0.71
    .'"
    -0.69
    )</
    -0.69
    '."
    -0.63
    netflix
    -0.62
    .).
    -0.61
    POSITIVE LOGITS
    ometimes
    0.50
    ggles
    0.46
    issance
    0.43
    Picture
    0.41
    ':
    0.40
     GEAR
    0.40
    aples
    0.40
    arching
    0.40
    iquette
    0.39
    owship
    0.39
    Act Density 2.490%

    No Known Activations