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

    Neuronpedia

    INDEX
    Explanations

    specific years or dates

    oai_token-act-pair · gpt-3.5-turbo

    specific timestamps and significant historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     abound
    -0.76
     differ
    -0.69
    ciples
    -0.67
    ographies
    -0.67
     profession
    -0.65
     simplify
    -0.63
    aintain
    -0.63
     themes
    -0.63
    ibilities
    -0.63
     principals
    -0.63
    POSITIVE LOGITS
     1954
    0.91
     February
    0.89
     Feb
    0.87
     1924
    0.86
     April
    0.84
     1962
    0.84
     September
    0.84
     2002
    0.84
     2004
    0.84
     December
    0.83
    Act Density 0.479%

    No Known Activations