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

    Neuronpedia

    INDEX
    Explanations

    specific terms or concepts related to research or documentation

    oai_token-act-pair · gpt-3.5-turbo

    references to previous works or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stairs
    -0.70
     scissors
    -0.64
     ultraviolet
    -0.62
     everyday
    -0.60
    adena
    -0.58
    ordinate
    -0.57
     tomorrow
    -0.57
     tonight
    -0.55
    liga
    -0.55
    ãĤ¦
    -0.55
    POSITIVE LOGITS
     tended
    0.78
     eras
    0.77
     installments
    0.76
     relied
    0.76
     iterations
    0.74
     failed
    0.73
     administrations
    0.69
    ptions
    0.68
     incarnation
    0.68
    inctions
    0.67
    Act Density 0.232%

    No Known Activations