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

    Neuronpedia

    INDEX
    Explanations

    verbs that involve action or intention

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating complex relationships between actions or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forced
    -0.70
    thought
    -0.68
    kson
    -0.68
    bidden
    -0.67
    cedented
    -0.62
    quished
    -0.62
    prints
    -0.62
    cloth
    -0.61
    got
    -0.61
    rolled
    -0.60
    POSITIVE LOGITS
     minimize
    1.36
     participate
    1.31
     engage
    1.30
     create
    1.28
     avoid
    1.28
     promote
    1.26
     maximize
    1.26
     formulate
    1.25
     manipulate
    1.24
     reduce
    1.24
    Act Density 0.576%

    No Known Activations