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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events happening at a specific time or in a specific sequence

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments and criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reborn
    -0.81
     Rounds
    -0.81
     Reloaded
    -0.79
    Ń·
    -0.77
    ļéĨĴ
    -0.75
     Dickinson
    -0.74
     Rica
    -0.67
     Liang
    -0.66
    erella
    -0.65
     Shooter
    -0.65
    POSITIVE LOGITS
    advertising
    1.03
    sized
    1.02
    distance
    0.98
    generation
    0.94
    suff
    0.91
    sent
    0.91
    dead
    0.91
    character
    0.90
    coord
    0.90
    pair
    0.90
    Act Density 0.211%

    No Known Activations