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

    Neuronpedia

    INDEX
    Explanations

    emotionally charged or impactful phrases or statements, possibly related to personal experiences or strong reactions

    oai_token-act-pair · gpt-3.5-turbo

    conversational phrases that express opinions or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heit
    -0.79
    abouts
    -0.77
    cca
    -0.68
    ady
    -0.67
    tyard
    -0.66
    osponsors
    -0.66
    erning
    -0.66
    ocobo
    -0.65
     woo
    -0.65
     officially
    -0.64
    POSITIVE LOGITS
    Changes
    0.87
    Prof
    0.83
    SPONSORED
    0.83
    Certain
    0.83
    Instead
    0.82
    Region
    0.81
    Secondly
    0.80
    However
    0.78
    Therefore
    0.78
    )"
    0.77
    Act Density 0.172%

    No Known Activations