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

    Neuronpedia

    INDEX
    Explanations

    references to authority figures, particularly elders and their influence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.49
     kaarangay
    -0.39
     tou
    -0.38
     Tou
    -0.37
     Tour
    -0.37
     Donnelly
    -0.36
     fantasy
    -0.35
     bot
    -0.35
     pitched
    -0.35
     utility
    -0.35
    POSITIVE LOGITS
     seniors
    0.95
     elders
    0.94
     elder
    0.87
    Seniors
    0.82
     Elders
    0.81
    elder
    0.80
     Seniors
    0.79
     Elder
    0.79
    istic
    0.77
     senior
    0.71
    Act Density 0.578%

    No Known Activations