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

    Neuronpedia

    INDEX
    Explanations

    the name "Tom" preceded by various other words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    the name "Tom" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gazette
    -0.70
    Ĥİ
    -0.70
    wrapper
    -0.66
    draft
    -0.65
    âĸ¬
    -0.65
    shapeshifter
    -0.64
    ylon
    -0.64
     td
    -0.63
     abiding
    -0.62
    xual
    -0.62
    POSITIVE LOGITS
    atoes
    1.29
    Tom
    1.00
     Clancy
    0.97
    oya
    0.96
    orrow
    0.92
    atsu
    0.91
    itan
    0.91
     Cruise
    0.88
    othy
    0.87
    ás
    0.84
    Act Density 0.016%

    No Known Activations