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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals in a political or investigative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.64
    FormTagHelper
    -0.60
     pleaſure
    -0.57
    onOptions
    -0.54
     uſe
    -0.54
     viſ
    -0.54
    #
    -0.54
     resear
    -0.53
     gevol
    -0.53
     Jefus
    -0.52
    POSITIVE LOGITS
     reassure
    0.95
     emphasize
    0.92
     reassuring
    0.92
     emphasis
    0.86
     emphasizing
    0.86
     Emphas
    0.86
    emphas
    0.84
     minimizing
    0.84
     minimized
    0.82
     reassured
    0.82
    Act Density 0.315%

    No Known Activations