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

    Neuronpedia

    INDEX
    Explanations

    actions related to orders and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Giving instructions or orders

    np_acts-logits-general · gemini-2.0-flash

    giving orders or instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хьтан
    -0.72
     Obrador
    -0.66
     grantor
    -0.63
     يتيمه
    -0.63
     Lordships
    -0.63
    WebVitals
    -0.59
     BorderRadius
    -0.58
    aarrggbb
    -0.58
    bootstrapcdn
    -0.58
    derry
    -0.57
    POSITIVE LOGITS
     subordinates
    0.62
     instructions
    0.51
     staff
    0.51
    Étymologie
    0.50
     instructed
    0.50
    手下
    0.50
     mọi
    0.50
    咐
    0.49
     employees
    0.47
     détaillés
    0.47
    Act Density 0.244%

    No Known Activations