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

    Neuronpedia

    INDEX
    Explanations

    organizations and groups

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "for" followed by various nouns and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mare
    -0.80
    mort
    -0.71
     gorge
    -0.70
    eus
    -0.66
    onen
    -0.65
    zona
    -0.65
     lashes
    -0.64
     cit
    -0.63
    stones
    -0.62
     clich
    -0.61
    POSITIVE LOGITS
    bidden
    0.91
     Equality
    0.85
     Sustainable
    0.81
     Peace
    0.81
     Action
    0.78
     Exploration
    0.78
     Accountability
    0.77
     Attribution
    0.77
     Testing
    0.76
     Inspection
    0.75
    Act Density 0.046%

    No Known Activations