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

    Neuronpedia

    INDEX
    Explanations

    mentions of time and political figures

    oai_token-act-pair · gpt-3.5-turbo

    numerical expressions or figures related to financial or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     psychiat
    -0.94
     arrang
    -0.78
    soDeliveryDate
    -0.75
     describ
    -0.72
     behav
    -0.72
    emale
    -0.72
     estab
    -0.71
    orage
    -0.68
    campus
    -0.65
    ffield
    -0.65
    POSITIVE LOGITS
     Oops
    0.82
     UPDATE
    0.79
    POR
    0.78
     ·
    0.74
     SHARES
    0.74
     PDT
    0.70
     Polit
    0.66
     Tough
    0.66
     [+
    0.66
     CST
    0.65
    Act Density 0.100%

    No Known Activations