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

    Neuronpedia

    INDEX
    Explanations

    phrases related to possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific frequently mentioned articles and demonstratives in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    """
    -0.66
     Bridges
    -0.64
     Walls
    -0.64
     Examples
    -0.60
     Rounds
    -0.59
     ende
    -0.59
    ÄŁ
    -0.59
    []
    -0.57
     Wade
    -0.56
     Sik
    -0.56
    POSITIVE LOGITS
    same
    0.90
     utmost
    0.86
     dreaded
    0.84
    oneliness
    0.76
     elusive
    0.72
    elin
    0.72
    ocratic
    0.71
    odic
    0.70
     usual
    0.69
     proverbial
    0.68
    Act Density 0.493%

    No Known Activations