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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "think" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Audiodateien
    -0.72
    ypep
    -0.66
    ExecuteReader
    -0.66
     Isaacs
    -0.66
    SizeMode
    -0.64
     δὲ
    -0.64
    Especificações
    -0.64
    rahi
    -0.63
    heber
    -0.62
    popd
    -0.62
    POSITIVE LOGITS
     think
    3.36
    Think
    3.06
     Think
    3.05
    think
    3.05
     THINK
    2.82
    THINK
    2.71
     thinks
    2.71
     thought
    2.02
     Thought
    1.77
    thought
    1.75
    Act Density 0.072%

    No Known Activations