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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.62
    ORAGE
    -0.61
     Inscrivez
    -0.59
    setViewportView
    -0.59
     للمعارف
    -0.58
    Suara
    -0.57
    Vidite
    -0.56
    ÈME
    -0.54
    глежда
    -0.53
    archiviato
    -0.52
    POSITIVE LOGITS
    fjspx
    0.72
    OGND
    0.69
     [*]
    0.61
     مشين
    0.60
     @"/
    0.59
    Diweddarwch
    0.58
    extAlignment
    0.57
    platin
    0.56
     nakalista
    0.54
    ("</
    0.54
    Act Density 1.263%

    No Known Activations