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

    Neuronpedia

    INDEX
    Explanations

    expressions of inner thoughts and realizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carrillo
    -0.56
     springfox
    -0.55
     Wilber
    -0.54
     maux
    -0.52
    Zacks
    -0.51
    摘要
    -0.50
     législ
    -0.50
     taurus
    -0.49
    PhysRevD
    -0.49
     Norwalk
    -0.48
    POSITIVE LOGITS
    GEBURTSDATUM
    0.85
     thought
    0.80
    thought
    0.78
    Thought
    0.74
    以为
    0.73
     Thought
    0.72
    以為
    0.71
     tưởng
    0.66
     THOUGHT
    0.65
    verwijspagina
    0.64
    Act Density 0.206%

    No Known Activations