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

    Neuronpedia

    INDEX
    Explanations

    references to academic institutions or specific schools within universities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of educational institutions, specifically schools and their departments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    女
    -0.71
    CRIP
    -0.66
    ãģį
    -0.62
     ease
    -0.58
     reinforcements
    -0.58
     disadvantage
    -0.56
     territ
    -0.55
     prin
    -0.55
     toget
    -0.54
     acknow
    -0.53
    POSITIVE LOGITS
     of
    1.06
     Of
    0.91
    Of
    0.87
    of
    0.83
     OF
    0.78
     thereof
    0.77
    sonian
    0.72
    craft
    0.71
    oft
    0.70
    odox
    0.69
    Act Density 0.050%

    No Known Activations