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

    Neuronpedia

    INDEX
    Explanations

    expressions related to thought processes and reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.73
    drücken
    -0.69
    FilterChain
    -0.69
    5
    -0.67
    legungen
    -0.67
    1
    -0.66
    тельству
    -0.65
    ers
    -0.64
    anlagen
    -0.64
    рыва
    -0.64
    POSITIVE LOGITS
     Thought
    1.31
     THOUGHT
    1.30
    thought
    1.24
    Thought
    1.19
     thought
    1.09
    thoughts
    1.06
     thoughts
    1.02
     SOT
    0.98
     Thoughts
    0.98
    Manbalar
    0.86
    Act Density 0.059%

    No Known Activations