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

    Neuronpedia

    INDEX
    Explanations

    facts or descriptions related to personal interactions and relationships

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.80
     diving
    -0.72
     scrap
    -0.69
     Cent
    -0.69
     estranged
    -0.67
     dissu
    -0.67
     endeav
    -0.62
     engagement
    -0.61
     wanting
    -0.61
    xual
    -0.61
    POSITIVE LOGITS
    ³³³³³³³³
    1.26
    ³³³
    1.24
    ³³³³³³³³³³³³³³³³
    1.20
    ³³³³
    1.19
    Posted
    1.15
    ³³
    0.99
    Contents
    0.98
    posted
    0.97
    Ingredients
    0.92
    Anonymous
    0.90
    Act Density 1.270%

    No Known Activations