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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical strength and capability

    oai_token-act-pair · gpt-3.5-turbo

    references to power in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Von
    -0.84
    romeda
    -0.78
     Debor
    -0.74
    eryl
    -0.73
     Bei
    -0.73
     Admission
    -0.71
    ALK
    -0.71
     Kitt
    -0.69
     Observ
    -0.67
    roit
    -0.66
    POSITIVE LOGITS
    stroke
    0.99
    houses
    0.96
     outage
    0.93
    train
    0.92
    lifting
    0.92
    Reviewer
    0.92
    chair
    0.85
    plant
    0.84
    boats
    0.84
    grid
    0.83
    Act Density 0.035%

    No Known Activations