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

    Neuronpedia

    INDEX
    Explanations

    emotional and introspective language related to belief and consideration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContentAsync
    -0.58
     Audiodateien
    -0.56
     disponibilità
    -0.49
     descrição
    -0.49
     dàng
    -0.47
     unfailing
    -0.46
    -0.46
     understatement
    -0.46
    keyframes
    -0.46
     endereço
    -0.46
    POSITIVE LOGITS
     thought
    2.31
     think
    2.26
    thought
    2.16
     THINK
    2.15
     Thought
    2.11
    think
    2.08
     THOUGHT
    2.05
     Think
    2.05
    Thought
    2.04
     thinking
    2.02
    Act Density 0.293%

    No Known Activations