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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the significance or necessity of certain actions or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -1.05
     nawr
    -1.03
     autorytatywna
    -1.02
    quelize
    -0.99
     Majefty
    -0.92
     дописавши
    -0.87
    RenderAtEndOf
    -0.87
    ValueStyle
    -0.86
     препратки
    -0.86
    tvguidetime
    -0.86
    POSITIVE LOGITS
     to
    0.81
     that
    0.71
    ,
    0.54
    es
    0.53
     people
    0.51
     for
    0.50
     the
    0.49
    '
    0.48
     time
    0.47
     bagi
    0.47
    Act Density 0.221%

    No Known Activations