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

    Neuronpedia

    INDEX
    Explanations

    imperative phrases that express a desire or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     daudz
    -0.75
    fiés
    -0.66
    FORMAN
    -0.66
    vats
    -0.65
    绝
    -0.61
     cobra
    -0.59
    えもん
    -0.59
    Rotating
    -0.59
     qualifié
    -0.58
     Josephine
    -0.58
    POSITIVE LOGITS
     wanna
    0.91
    wanna
    0.89
     Wanna
    0.83
    Wanna
    0.83
     estimés
    0.81
    ագրություններ
    0.79
    setupUi
    0.79
     querem
    0.79
     voulez
    0.76
    mazoo
    0.75
    Act Density 0.105%

    No Known Activations