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

    Neuronpedia

    INDEX
    Explanations

    words related to circuits or routes

    oai_token-act-pair · gpt-3.5-turbo

    references to "circuit" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minster
    -0.75
    ipple
    -0.73
    ACTED
    -0.70
    ever
    -0.66
    ighter
    -0.66
    gets
    -0.63
    ledged
    -0.63
    ipeg
    -0.62
    umar
    -0.62
     Haku
    -0.61
    POSITIVE LOGITS
     breaker
    1.09
     circuits
    0.88
    eering
    0.81
    eer
    0.79
     boards
    0.79
     circuit
    0.77
    dayName
    0.75
     Racer
    0.75
    engers
    0.75
    displayText
    0.73
    Act Density 0.022%

    No Known Activations