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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a specific event or situation that is in focus

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this" and its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worms
    -0.72
    icons
    -0.72
    vae
    -0.70
    doms
    -0.67
    ickets
    -0.66
    rh
    -0.64
    nets
    -0.62
    okers
    -0.62
    ãĤ¹ãĥĪ
    -0.62
    pots
    -0.62
    POSITIVE LOGITS
     week
    1.06
     month
    0.96
     year
    0.95
     morning
    0.87
     afternoon
    0.87
     weekend
    0.85
     latest
    0.82
     century
    0.76
     episode
    0.75
     WEEK
    0.75
    Act Density 0.248%

    No Known Activations