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

    Neuronpedia

    INDEX
    Explanations

    second person pronouns and verbs related to requests or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.73
    RectangleBorder
    -0.66
    CloseOperation
    -0.63
    ineno
    -0.62
     Roumanie
    -0.59
     BoxFit
    -0.59
    StoryboardSegue
    -0.58
    ładka
    -0.58
     Données
    -0.58
     onPostExecute
    -0.56
    POSITIVE LOGITS
     prefer
    0.63
     ever
    0.62
     lucky
    0.55
     ✭✭
    0.55
     forget
    0.55
     don
    0.52
     luck
    0.51
     insist
    0.50
     fan
    0.50
     wanna
    0.50
    Act Density 0.108%

    No Known Activations