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

    Neuronpedia

    INDEX
    Explanations

    references to power dynamics and political negotiations

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

    preceding modal verbs

    np_acts-logits-general · gemini-2.0-flash

    modal verbs followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     showcasing
    -0.94
     showcased
    -0.88
     prioritize
    -0.88
     impactful
    -0.87
     incentiv
    -0.85
     onboarding
    -0.83
     transitioning
    -0.82
     prioritizing
    -0.82
     referencing
    -0.81
     leveraging
    -0.79
    POSITIVE LOGITS
     daß
    0.84
     skall
    0.77
     muß
    0.76
     läßt
    0.67
    faßt
    0.65
     Himo
    0.64
     mußte
    0.62
     daardoor
    0.60
     rospy
    0.59
     doubtless
    0.58
    Act Density 0.695%

    No Known Activations