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

    Neuronpedia

    INDEX
    Explanations

    references to specific years within various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the progression of time, particularly related to years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zsche
    -0.82
    vironment
    -0.75
    ernand
    -0.71
    overty
    -0.70
     Desk
    -0.70
    eday
    -0.68
    irie
    -0.67
    mercial
    -0.66
    urtles
    -0.66
    adena
    -0.66
    POSITIVE LOGITS
     anniversary
    0.83
    eve
    0.78
    anza
    0.71
    frames
    0.70
    ear
    0.69
    long
    0.68
    nings
    0.67
     olds
    0.67
    chan
    0.66
    %%
    0.65
    Act Density 0.091%

    No Known Activations