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

    Neuronpedia

    INDEX
    Explanations

    phrases related to power dynamics and leadership instability

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

    loss of support or reputation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -0.43
    |}{}
    -0.38
    Портал
    -0.37
    cydow
    -0.36
    ntö
    -0.34
    habitude
    -0.34
    bias
    -0.34
     يتيمه
    -0.33
    örté
    -0.33
    WebKit
    -0.33
    POSITIVE LOGITS
     unpopular
    0.86
     credibility
    0.70
     popularity
    0.66
     weakened
    0.66
     weakening
    0.65
     weakens
    0.63
     desgaste
    0.62
     reelection
    0.60
     reputation
    0.60
     weaken
    0.60
    Act Density 0.098%

    No Known Activations