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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential or uncertain outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.66
     invokingState
    -0.61
    --]
    -0.54
    viewDidLoad
    -0.51
    RenderAtEndOf
    -0.51
    IsMutable
    -0.50
    WHILE
    -0.48
    WebVitals
    -0.48
     Италијани
    -0.48
    While
    -0.46
    POSITIVE LOGITS
    rungsseite
    0.81
     defaultstate
    0.60
     сожалению
    0.56
    lccn
    0.54
    latego
    0.52
     примеру
    0.52
    舺
    0.52
     kasarigan
    0.51
     oorsp
    0.51
     revanche
    0.50
    Act Density 0.592%

    No Known Activations