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

    Neuronpedia

    INDEX
    Explanations

    verbs in past tense

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "said."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pont
    -0.80
    à¦
    -0.76
    Translation
    -0.74
    tumblr
    -0.74
    ε
    -0.71
    kay
    -0.70
    «
    -0.70
    Pages
    -0.69
    ãĤ«
    -0.69
    ãĥĬ
    -0.68
    POSITIVE LOGITS
     anecd
    0.82
     Tuesday
    0.71
     Monday
    0.71
     he
    0.71
     Thursday
    0.71
     Wednesday
    0.70
     there
    0.69
     yesterday
    0.68
     bluntly
    0.68
     goodbye
    0.67
    Act Density 0.170%

    No Known Activations