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

    Neuronpedia

    INDEX
    Explanations

    words related to high energy levels and principled behavior

    oai_token-act-pair · gpt-3.5-turbo

    terms related to energy levels and principled behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    redit
    -0.85
    iosis
    -0.78
    oan
    -0.78
    obyl
    -0.77
    forest
    -0.72
    ingu
    -0.72
     Dunham
    -0.72
    VPN
    -0.71
    ocaust
    -0.70
    oil
    -0.68
    POSITIVE LOGITS
     enough
    0.84
     spirited
    0.82
     energetic
    0.81
    nesses
    0.78
    looking
    0.73
     lively
    0.71
    glers
    0.71
    ness
    0.70
     little
    0.69
     adventurer
    0.67
    Act Density 0.024%

    No Known Activations