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

    Neuronpedia

    INDEX
    Explanations

    instances of progression and improvement over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ComVisible
    -0.61
    aima
    -0.52
     nying
    -0.50
     taşı
    -0.49
     Puy
    -0.49
     lontano
    -0.49
     vícti
    -0.48
     trần
    -0.48
     angepasst
    -0.47
    yen
    -0.47
    POSITIVE LOGITS
    後半
    0.84
     Daarna
    0.72
    ValueStyle
    0.71
     late
    0.68
    Geplaatst
    0.67
    IntoConstraints
    0.65
    complexContent
    0.64
     تضيفلها
    0.64
    后期
    0.63
     later
    0.63
    Act Density 0.312%

    No Known Activations