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

    Neuronpedia

    INDEX
    Explanations

    the word "to" followed by another word or a number, potentially related to expectations or obligations

    oai_token-act-pair · gpt-3.5-turbo

    expectations or duties related to events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Appears
    -0.71
     Compass
    -0.68
     Tens
    -0.67
     quotations
    -0.66
    iple
    -0.63
     Levi
    -0.62
     Surge
    -0.61
    river
    -0.61
     conceptions
    -0.60
     Kis
    -0.58
    POSITIVE LOGITS
     be
    0.98
     behave
    0.94
     solve
    0.92
     protect
    0.91
     embody
    0.88
     represent
    0.88
     compensate
    0.88
     equate
    0.87
     adhere
    0.86
     defend
    0.86
    Act Density 0.081%

    No Known Activations