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

    Neuronpedia

    INDEX
    Explanations

    references to specific holidays, particularly Thanksgiving

    oai_token-act-pair · gpt-3.5-turbo

    references to Thanksgiving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     orb
    -0.68
    sten
    -0.67
     labelled
    -0.65
     pursu
    -0.64
     armour
    -0.64
    CL
    -0.64
    ilib
    -0.64
     meters
    -0.63
    peer
    -0.62
     metre
    -0.62
    POSITIVE LOGITS
     Thanksgiving
    3.79
     Christmas
    1.89
     turkey
    1.85
    Christmas
    1.60
     holiday
    1.52
     holidays
    1.49
     Halloween
    1.47
     Easter
    1.37
    holiday
    1.30
     Holiday
    1.25
    Act Density 0.014%

    No Known Activations