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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "energy" and related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to vitality and enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.88
    gery
    -0.83
    ãĥīãĥ©
    -0.80
    ettings
    -0.77
     Doct
    -0.70
    geries
    -0.69
     Settlement
    -0.63
    glers
    -0.63
     Cause
    -0.62
    ournal
    -0.62
    POSITIVE LOGITS
     energy
    0.83
     energ
    0.80
    fulness
    0.78
     powering
    0.77
     Enhancement
    0.77
     expended
    0.75
     drinks
    0.75
    igue
    0.72
    energy
    0.72
     capacitor
    0.71
    Act Density 0.020%

    No Known Activations