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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "thought" and its related forms, focusing on the quality and depth of ideas expressed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    
    -0.82
    er
    -0.81
    ers
    -0.71
     daly
    -0.71
    o
    -0.70
     Daly
    -0.70
    rý
    -0.69
    legungen
    -0.69
    lgica
    -0.69
    drücken
    -0.68
    POSITIVE LOGITS
     Thought
    1.74
    thought
    1.69
     THOUGHT
    1.66
    Thought
    1.64
     thought
    1.61
    thoughts
    1.26
     thoughts
    1.21
     Thoughts
    1.09
    Thoughts
    1.00
     THOUGHTS
    0.99
    Act Density 0.104%

    No Known Activations