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

    Neuronpedia

    INDEX
    Explanations

    years and numbers indicating accomplishments or awards

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     awoke
    -0.74
    tip
    -0.74
    isphere
    -0.69
    advertisement
    -0.64
    inventoryQuantity
    -0.64
    iquid
    -0.64
    GROUND
    -0.63
    oldown
    -0.63
     intens
    -0.63
     è£ıè
    -0.62
    POSITIVE LOGITS
     1997
    1.21
     1998
    1.18
     1988
    1.15
     1996
    1.14
     1987
    1.13
     1995
    1.13
     1978
    1.12
     2003
    1.11
     2002
    1.11
     1999
    1.11
    Act Density 0.134%

    No Known Activations