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

    Neuronpedia

    INDEX
    Explanations

    affirmations or confirmations of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -0.75
     Salvatore
    -0.75
    ^(@)
    -0.74
     FOS
    -0.74
     Maren
    -0.73
     Efq
    -0.73
     Moslem
    -0.73
    AntiForgeryToken
    -0.70
     LOS
    -0.69
     }}">
    -0.69
    POSITIVE LOGITS
     indeed
    1.77
    indeed
    1.69
    Indeed
    1.62
     Indeed
    1.61
    的确
    0.86
    确实
    0.81
    確實
    0.76
     inderdaad
    0.73
     fact
    0.73
    的確
    0.71
    Act Density 0.082%

    No Known Activations