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

    Neuronpedia

    INDEX
    Explanations

    phrases related to forming opinions or perspectives on something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "impression"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.72
     hips
    -0.69
    regulated
    -0.67
    yss
    -0.64
     planning
    -0.62
     legalized
    -0.62
     plotted
    -0.62
     intensive
    -0.61
     filing
    -0.61
    iding
    -0.61
    POSITIVE LOGITS
     impression
    1.41
     impressions
    1.22
    IELD
    0.79
    uren
    0.78
    -+-+
    0.75
    ROR
    0.74
     perceptions
    0.71
     Wiz
    0.71
    ãĥ¼ãĥĨ
    0.71
    RECT
    0.71
    Act Density 0.006%

    No Known Activations