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

    Neuronpedia

    INDEX
    Explanations

    words related to physical strength

    oai_token-act-pair · gpt-3.5-turbo

    references to physical strength and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     externalToEVAOnly
    -0.88
    romeda
    -0.79
    cise
    -0.79
    eor
    -0.76
    rodu
    -0.74
    rea
    -0.73
    rez
    -0.72
    agraph
    -0.71
    mony
    -0.70
    alus
    -0.69
    POSITIVE LOGITS
     Flavoring
    0.93
     strength
    0.92
    ament
    0.84
     cryptography
    0.75
    IER
    0.73
    manship
    0.72
    fast
    0.72
     weakest
    0.72
    building
    0.72
     handshake
    0.72
    Act Density 0.041%

    No Known Activations