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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating expectations or obligations

    oai_token-act-pair · gpt-3.5-turbo

    references to expectations or obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fram
    -0.69
    quickShipAvailable
    -0.66
     Nationwide
    -0.66
    Textures
    -0.65
    river
    -0.63
     Wid
    -0.62
     Compass
    -0.59
     Volks
    -0.58
     Sets
    -0.58
     Harris
    -0.57
    POSITIVE LOGITS
     behave
    1.06
     be
    1.03
     embody
    1.02
     represent
    0.94
     abide
    0.93
     compete
    0.89
     mimic
    0.88
     adhere
    0.88
     fend
    0.88
     belong
    0.87
    Act Density 0.088%

    No Known Activations