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

    Neuronpedia

    INDEX
    Explanations

    scientific research-related terms and findings

    oai_token-act-pair · gpt-3.5-turbo

    instances of words related to documentation and reporting of scientific findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fin
    -0.65
    tails
    -0.62
     takedown
    -0.62
     inbox
    -0.62
    awk
    -0.60
     gears
    -0.60
    endar
    -0.59
    sheets
    -0.59
    ajo
    -0.58
    claimer
    -0.58
    POSITIVE LOGITS
     Qiao
    0.89
     clinically
    0.84
    ãĥ¼ãĥĨ
    0.83
     anecd
    0.80
     psychiat
    0.79
     Parenthood
    0.77
    ãĤ´
    0.75
     anew
    0.73
     scientifically
    0.71
    Ú
    0.69
    Act Density 0.154%

    No Known Activations