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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to control, such as "control signals", "control panel", and "control tower"

    oai_token-act-pair · gpt-3.5-turbo

    references to control systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gow
    -0.84
    ich
    -0.66
    neys
    -0.65
     Masquerade
    -0.64
     mc
    -0.64
    iscopal
    -0.63
    osp
    -0.63
    à¤
    -0.62
    anthrop
    -0.62
     Beir
    -0.62
    POSITIVE LOGITS
     freak
    0.92
     valves
    0.80
     valve
    0.80
    eer
    0.80
     rods
    0.76
     exercised
    0.74
     levers
    0.73
     fre
    0.72
     exerted
    0.72
    eers
    0.72
    Act Density 0.063%

    No Known Activations