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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical strength and power

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "strength"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    romeda
    -0.85
     externalToEVAOnly
    -0.85
    eor
    -0.80
    rez
    -0.76
    rodu
    -0.75
    rea
    -0.75
    alus
    -0.72
    cise
    -0.71
    reon
    -0.70
    apolis
    -0.70
    POSITIVE LOGITS
     Flavoring
    0.97
     strength
    0.90
    ament
    0.79
     cryptography
    0.75
     handshake
    0.75
    manship
    0.73
     weakest
    0.72
    IER
    0.72
    fast
    0.70
     bargaining
    0.68
    Act Density 0.030%

    No Known Activations