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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs that express affirmation or agreement

    oai_token-act-pair · gpt-3.5-turbo

    sentences expressing opinions and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    });
    -0.73
     furthermore
    -0.67
     moreover
    -0.62
    estamp
    -0.62
     Additionally
    -0.60
    mentioned
    -0.60
    idon
    -0.59
    breaking
    -0.58
    ï¸ı
    -0.57
     recognizes
    -0.57
    POSITIVE LOGITS
     merely
    0.92
     purely
    0.89
     elsewhere
    0.77
     mere
    0.75
     relegated
    0.75
     concentrate
    0.74
     passively
    0.71
     simply
    0.71
     concentrated
    0.71
     obscurity
    0.71
    Act Density 1.102%

    No Known Activations