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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate duration or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    n
    -0.74
    a
    -0.72
     “
    -0.68
    et
    -0.66
    ’
    -0.65
     –
    -0.64
    1
    -0.63
     D
    -0.63
    ia
    -0.63
    чин
    -0.62
    POSITIVE LOGITS
    throughout
    1.78
     throughout
    1.59
    HOUT
    1.36
     Throughout
    1.35
    Throughout
    1.35
    MLLoader
    1.18
     تضيفلها
    1.15
     defaultstate
    1.09
    ostante
    1.08
     sepanjang
    1.07
    Act Density 0.068%

    No Known Activations