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

    Neuronpedia

    INDEX
    Explanations

    words related to thoughts and thinking processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ing
    -0.65
    териалы
    -0.60
    heimer
    -0.57
    🚨
    -0.55
    oled
    -0.54
    o
    -0.54
    ❒
    -0.52
    ING
    -0.52
     Allí
    -0.52
    ody
    -0.51
    POSITIVE LOGITS
    fulness
    1.03
     provoking
    0.99
     THOUGHT
    0.97
    Thought
    0.96
     Thought
    0.94
    provoking
    0.93
    thought
    0.90
    thoughts
    0.77
    itinéraire
    0.77
     Roskov
    0.75
    Act Density 0.101%

    No Known Activations