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

    Neuronpedia

    INDEX
    Explanations

    words related to energy and power

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "energy."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rises
    -0.73
     Scrib
    -0.68
     Clerk
    -0.67
     Blow
    -0.64
    iles
    -0.60
    roads
    -0.59
    smith
    -0.59
    ering
    -0.59
     Reincarn
    -0.58
    eros
    -0.58
    POSITIVE LOGITS
    getic
    1.23
    atives
    1.04
    ative
    0.96
    iatus
    0.90
    oute
    0.82
    atively
    0.81
    ation
    0.79
    aton
    0.79
    oneliness
    0.78
    bah
    0.77
    Act Density 0.066%

    No Known Activations