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

    Neuronpedia

    INDEX
    Explanations

    words related to physical actions or aggressive behavior

    oai_token-act-pair · gpt-3.5-turbo

    words related to renewable energy and environmental topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oun
    -0.72
     unden
    -0.72
     skelet
    -0.67
    ĥ
    -0.65
     warr
    -0.64
    irc
    -0.64
    Ry
    -0.63
    ccording
    -0.62
    Mos
    -0.61
     newsp
    -0.61
    POSITIVE LOGITS
    berries
    0.87
    naire
    0.86
    naires
    0.83
    berry
    0.79
    worms
    0.79
    BACK
    0.77
    dale
    0.75
    ously
    0.72
    iflower
    0.70
     glances
    0.70
    Act Density 0.310%

    No Known Activations