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

    Neuronpedia

    INDEX
    Explanations

    dates or time periods, particularly from the mid-20th century onward

    oai_token-act-pair · gpt-3.5-turbo

    references to specific decades in the 20th century

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     masc
    -0.62
     Rivals
    -0.60
     medi
    -0.56
    aukee
    -0.55
     param
    -0.52
     ingred
    -0.49
    Dial
    -0.49
    ItemImage
    -0.49
     thoughts
    -0.48
     naturally
    -0.48
    POSITIVE LOGITS
    s
    1.63
    âĢ²
    1.32
    's
    1.12
    ÃŃs
    1.05
    ies
    0.93
    ties
    0.91
    ixties
    0.89
    psons
    0.88
    enthal
    0.87
    ´
    0.85
    Act Density 0.047%

    No Known Activations