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

    Neuronpedia

    INDEX
    Explanations

    the word "holiday"

    oai_token-act-pair · gpt-3.5-turbo

    references to holidays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Daniels
    -0.75
    anos
    -0.74
    nington
    -0.71
    ected
    -0.68
    ector
    -0.66
     Aden
    -0.66
    adle
    -0.65
    umbing
    -0.65
    ioch
    -0.65
    ect
    -0.64
    POSITIVE LOGITS
     holidays
    1.20
     holiday
    1.19
     Holiday
    1.02
    idays
    0.99
    iday
    0.96
    holiday
    0.89
     festive
    0.87
     weekend
    0.84
     vacation
    0.81
    Christmas
    0.81
    Act Density 0.009%

    No Known Activations