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

    Neuronpedia

    INDEX
    Explanations

    expressions of thought and contemplation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    k
    -0.79
    3
    -0.75
    kler
    -0.74
    5
    -0.66
     McCarthy
    -0.65
    h
    -0.65
    1
    -0.64
    ib
    -0.64
    7
    -0.62
     y
    -0.61
    POSITIVE LOGITS
    ConstraintMaker
    1.20
    Manbalar
    1.08
    gatsby
    1.01
    DockStyle
    0.96
     Thought
    0.95
     للمعارف
    0.94
     THOUGHT
    0.94
    thoughts
    0.92
     Thoughts
    0.91
    writeFieldEnd
    0.91
    Act Density 0.006%

    No Known Activations