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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating continuity or presence across multiple contexts or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pisa
    -0.64
    a
    -0.62
    Syracuse
    -0.62
    n
    -0.61
    Figure
    -0.59
     Crusoe
    -0.59
    ic
    -0.56
    urlopen
    -0.56
     Syracuse
    -0.56
    itan
    -0.55
    POSITIVE LOGITS
    throughout
    1.39
     throughout
    1.22
    HOUT
    1.15
     Throughout
    1.02
    Throughout
    1.00
     defaultstate
    0.94
     sepanjang
    0.93
     تضيفلها
    0.85
    athread
    0.84
    MLLoader
    0.77
    Act Density 0.069%

    No Known Activations