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

    Neuronpedia

    INDEX
    Explanations

    references to authority and institutional power, particularly in religious or governance contexts

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

    Followed by a past tense verb

    np_acts-logits-general · gemini-2.0-flash

    statements of fact or conclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transitioned
    -0.83
     transitioning
    -0.82
     referenced
    -0.78
     prioritizing
    -0.78
     referencing
    -0.77
     leveraging
    -0.73
     showcasing
    -0.73
     jobbet
    -0.73
     incentiv
    -0.72
     prioritized
    -0.72
    POSITIVE LOGITS
     skall
    0.83
     thereupon
    0.75
    MLLoader
    0.71
     giebt
    0.63
     thereto
    0.59
     forthwith
    0.58
     muß
    0.57
     mußte
    0.56
     daß
    0.56
    ところが
    0.55
    Act Density 0.704%

    No Known Activations