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

    Neuronpedia

    INDEX
    Explanations

    terms related to control and manipulation, especially in the context of technology and systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to control mechanisms in technology and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.78
    istle
    -0.68
    iversary
    -0.68
    iatus
    -0.67
    olit
    -0.66
    ruary
    -0.65
     jo
    -0.64
    ead
    -0.63
     Chrys
    -0.63
    ylan
    -0.63
    POSITIVE LOGITS
     levers
    0.89
     impulses
    0.79
     steering
    0.77
    eers
    0.77
     valve
    0.76
     valves
    0.76
    rollers
    0.75
     Commands
    0.74
    eering
    0.74
     freak
    0.73
    Act Density 0.030%

    No Known Activations