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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating large quantities or numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑģÑĭлки
    -0.15
    ewn
    -0.14
    zech
    -0.14
    ardo
    -0.14
    zier
    -0.14
    ë¦Ħ
    -0.14
    ìłĢ
    -0.13
    ÑħÑĸв
    -0.13
    nings
    -0.13
    inda
    -0.13
    POSITIVE LOGITS
     thousands
    0.20
    ijkstra
    0.17
     thousand
    0.15
    aines
    0.15
    ousse
    0.15
    rych
    0.15
    itant
    0.14
    -meta
    0.14
    iegel
    0.14
     fold
    0.14
    Act Density 0.018%

    No Known Activations