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

    Neuronpedia

    INDEX
    Explanations

    names of universities and educational institutions

    oai_token-act-pair · gpt-3.5-turbo

    names of countries and universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aroused
    -0.63
     Bes
    -0.55
     prec
    -0.55
     cryptocurrency
    -0.52
     ,"
    -0.52
    ?).
    -0.50
     Chapter
    -0.50
     ISI
    -0.49
     Slightly
    -0.49
     recommended
    -0.49
    POSITIVE LOGITS
    berra
    0.85
    £ı
    0.78
    agall
    0.74
    ona
    0.74
    rador
    0.73
    gb
    0.73
    anmar
    0.73
    undai
    0.72
    pherd
    0.71
    obar
    0.70
    Act Density 0.424%

    No Known Activations