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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the ability to take action and influence outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thro
    -0.15
    Controllers
    -0.15
    assen
    -0.14
    559
    -0.14
    aina
    -0.14
    stro
    -0.14
     oyn
    -0.14
    ncpy
    -0.14
    unas
    -0.14
    ader
    -0.14
    POSITIVE LOGITS
     tasks
    0.23
     acts
    0.20
     activities
    0.20
     deeds
    0.20
     unto
    0.19
    omba
    0.19
     Tasks
    0.19
    _activities
    0.18
    tasks
    0.17
     things
    0.17
    Act Density 0.098%

    No Known Activations