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

    Neuronpedia

    INDEX
    Explanations

    references to authority and decision-making within systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zemi
    -0.16
    UIScreen
    -0.15
    Forgery
    -0.14
    (ConfigurationManager
    -0.14
    feit
    -0.14
    463
    -0.14
    Äįit
    -0.14
    ãĤ¤ãĥĦ
    -0.14
    slaught
    -0.14
    phalt
    -0.14
    POSITIVE LOGITS
     Lov
    0.16
     provided
    0.15
     having
    0.15
     pen
    0.15
    .AF
    0.14
    ,
    0.14
     All
    0.14
     B
    0.14
    0.14
     Kings
    0.14
    Act Density 0.788%

    No Known Activations