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

    Neuronpedia

    INDEX
    Explanations

    references to authority figures and their relationships with subordinates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    colns
    -0.52
    jsonPath
    -0.49
    FormTagHelper
    -0.48
    xymatrix
    -0.48
    athread
    -0.48
    ituary
    -0.48
     electrolysis
    -0.48
     natale
    -0.48
     Roskov
    -0.47
    lably
    -0.47
    POSITIVE LOGITS
     authority
    0.76
    authority
    0.71
     arrogant
    0.70
     assertive
    0.63
     haughty
    0.62
     Authority
    0.62
     AUTHORITY
    0.62
     disrespectful
    0.59
     seniority
    0.59
    Authority
    0.59
    Act Density 0.396%

    No Known Activations