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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs related to personal experiences

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs describing actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pierre
    -0.70
    Brazil
    -0.67
    uesday
    -0.66
    adj
    -0.63
    ``
    -0.63
    +)
    -0.62
    MI
    -0.62
     Rio
    -0.62
    Trivia
    -0.60
    -0.59
    POSITIVE LOGITS
     earlier
    0.76
     previously
    0.74
    iless
    0.74
     exha
    0.71
     undermin
    0.71
     unintention
    0.67
     looph
    0.66
     beforehand
    0.66
    keyes
    0.66
     hitherto
    0.65
    Act Density 0.306%

    No Known Activations