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

    Neuronpedia

    INDEX
    Explanations

    references to scientific institutions or laboratories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of specific scientific facilities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     deduct
    -0.76
     misunder
    -0.70
     Rivera
    -0.67
    MpServer
    -0.66
    esting
    -0.64
     understatement
    -0.64
    ãģı
    -0.64
     Gould
    -0.64
     nodd
    -0.63
     veter
    -0.61
    POSITIVE LOGITS
     Bam
    0.75
    riot
    0.69
    ¿½
    0.69
    iege
    0.64
    kus
    0.64
    ICLE
    0.64
    lehem
    0.64
     Monteneg
    0.63
    adle
    0.62
    ggle
    0.62
    Act Density 0.000%

    No Known Activations