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

    Neuronpedia

    INDEX
    Explanations

    the name "Tom" with various suffixes or contexts

    oai_token-act-pair · gpt-3.5-turbo

    the name "Tom" in various contexts and mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     abiding
    -0.65
    shapeshifter
    -0.64
     imprisonment
    -0.63
     colleges
    -0.62
     heck
    -0.58
     lia
    -0.58
    ements
    -0.57
     academics
    -0.57
     provinces
    -0.57
    places
    -0.57
    POSITIVE LOGITS
    atoes
    1.39
    ás
    1.13
     Clancy
    1.10
    Dispatch
    1.08
    orrow
    1.05
    oya
    1.04
     Cruise
    1.00
    Tom
    0.97
    my
    0.96
    kinson
    0.94
    Act Density 0.016%

    No Known Activations