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

    Neuronpedia

    INDEX
    Explanations

    sentences containing the word "always."

    oai_token-act-pair · gpt-3.5-turbo

    recurring expressions of personal sentiments and repetitive phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Delivery
    -0.73
     representatives
    -0.64
     newcomer
    -0.62
     entry
    -0.62
    worthiness
    -0.62
    winner
    -0.61
     incumbent
    -0.61
     Parenthood
    -0.60
     Opposition
    -0.60
     entrants
    -0.60
    POSITIVE LOGITS
     myself
    1.31
     wondered
    1.28
     fantas
    1.23
     regretted
    1.19
     regret
    1.17
     wonder
    1.13
     think
    1.08
     wished
    1.04
     wish
    1.04
     thought
    1.02
    Act Density 0.224%

    No Known Activations