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

    Neuronpedia

    INDEX
    Explanations

    instances of support and collaboration across various sectors and initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otas
    -0.17
     nineteenth
    -0.16
     sevent
    -0.16
     twentieth
    -0.15
    ele
    -0.14
    eyen
    -0.14
     (£
    -0.14
    shal
    -0.14
     Twelve
    -0.14
    iyi
    -0.13
    POSITIVE LOGITS
     thousands
    0.68
     hundreds
    0.68
     Thousands
    0.52
     approximately
    0.50
     Hundreds
    0.49
     tens
    0.48
    Thousands
    0.45
    Hundreds
    0.44
     roughly
    0.44
    undreds
    0.42
    Act Density 1.659%

    No Known Activations