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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social interactions and community engagement

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    deen
    -1.09
    ossession
    -1.04
    dayName
    -1.04
     commute
    -1.03
     prol
    -0.97
    olation
    -0.95
    oulos
    -0.93
    dad
    -0.92
    ocene
    -0.90
    ysc
    -0.89
    POSITIVE LOGITS
     Tradable
    1.12
     whom
    1.12
    warts
    1.00
     those
    1.00
    %%%%
    0.98
    addons
    0.94
    etooth
    0.94
     Scout
    0.92
     Scouts
    0.91
     among
    0.90
    Act Density 0.460%

    No Known Activations