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

    Neuronpedia

    INDEX
    Explanations

    phrases related to power-related activities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to power plays in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apest
    -0.75
     Obj
    -0.71
     IMAGES
    -0.70
    Ĭ±
    -0.69
    wcsstore
    -0.69
     Nationwide
    -0.68
    opian
    -0.67
    lish
    -0.67
    traumatic
    -0.66
    alus
    -0.64
    POSITIVE LOGITS
     ignition
    0.87
    achev
    0.81
     amplification
    0.80
     pedals
    0.76
    ifting
    0.75
    tein
    0.75
    PDATE
    0.74
     amplifier
    0.74
     levers
    0.73
    ierrez
    0.73
    Act Density 0.259%

    No Known Activations