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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the concept of control

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to control or manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ich
    -0.79
    istle
    -0.78
    olit
    -0.74
    olid
    -0.73
     Gleaming
    -0.70
    tom
    -0.70
    ithing
    -0.69
    itched
    -0.68
    eds
    -0.68
     à¤
    -0.68
    POSITIVE LOGITS
     levers
    0.88
     controlled
    0.79
     tempo
    0.77
     steering
    0.76
     contro
    0.74
     freak
    0.73
     controlling
    0.73
    eering
    0.72
     impulses
    0.72
     ventilation
    0.68
    Act Density 0.040%

    No Known Activations