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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities related to time and count

    oai_token-act-pair · gpt-3.5-turbo

    references to structured sequences or cycles in events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sov
    -0.71
    adem
    -0.65
    mobi
    -0.65
    NetMessage
    -0.64
     consortium
    -0.64
    arty
    -0.63
    egu
    -0.61
    umbn
    -0.60
    ortium
    -0.60
    culosis
    -0.58
    POSITIVE LOGITS
     thereafter
    1.06
     thereof
    1.05
     of
    0.88
     individually
    0.86
     preceding
    0.81
     consecut
    0.80
     onwards
    0.78
     elapsed
    0.75
     imaginable
    0.73
     spent
    0.72
    Act Density 0.185%

    No Known Activations