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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing certainty or assurance

    oai_token-act-pair · gpt-3.5-turbo

    confident assertions or affirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.76
    vernment
    -0.68
    âĵĺ
    -0.67
    çīĪ
    -0.66
    mercial
    -0.66
    士
    -0.64
     entrusted
    -0.62
    çĶ°
    -0.61
    EGIN
    -0.60
    perse
    -0.60
    POSITIVE LOGITS
    ndra
    0.83
    ples
    0.72
    ties
    0.70
    zon
    0.69
    arat
    0.67
    fire
    0.67
     tack
    0.67
    itri
    0.66
     enough
    0.66
    rays
    0.66
    Act Density 0.015%

    No Known Activations