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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "mac" in the text

    oai_token-act-pair · gpt-3.5-turbo

    descriptors indicating extreme negative outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phia
    -0.76
     Defeat
    -0.75
    urers
    -0.71
     corro
    -0.69
    phy
    -0.67
    onen
    -0.66
    mons
    -0.66
     Antiqu
    -0.65
    uscript
    -0.64
     deceive
    -0.64
    POSITIVE LOGITS
    é»Ĵ
    0.75
    rawdownloadcloneembedreportprint
    0.68
     baths
    0.66
     BASE
    0.65
    ãĥĺãĥ©
    0.64
     pairs
    0.64
     GDDR
    0.63
    inous
    0.62
    /**
    0.61
    OTAL
    0.60
    Act Density 0.000%

    No Known Activations