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

    Neuronpedia

    INDEX
    Explanations

    expressions related to contemplation and reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nameof
    -0.14
    éra
    -0.14
    .bz
    -0.13
    ạ
    -0.13
     loc
    -0.13
     sect
    -0.13
    .Init
    -0.13
    -0.12
    ename
    -0.12
     incur
    -0.12
    POSITIVE LOGITS
     thought
    0.52
     thinking
    0.47
    thought
    0.46
    thinking
    0.45
     Thought
    0.45
     thoughts
    0.45
    æĢĿèĢĥ
    0.45
    think
    0.44
     THINK
    0.44
     Thinking
    0.43
    Act Density 0.416%

    No Known Activations