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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with giving instructions or reminders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -1.01
    FieldNumber
    -0.82
    νω
    -0.68
    ubli
    -0.67
    TargetException
    -0.67
     MotionEvent
    -0.63
    ghalaya
    -0.61
     Invis
    -0.60
    RectangleBorder
    -0.60
     imageUrl
    -0.59
    POSITIVE LOGITS
     обязательно
    0.70
     always
    0.67
    бяза
    0.67
     plenty
    0.66
    记得
    0.66
     mentioning
    0.66
     include
    0.63
    ly
    0.62
     habr
    0.61
    PerformLayout
    0.60
    Act Density 0.059%

    No Known Activations