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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that highlight differences or similarities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashvili
    -0.50
     hurtig
    -0.47
    そりゃ
    -0.47
    ільки
    -0.47
    nocześnie
    -0.46
    yntaxException
    -0.45
    不止
    -0.45
     falsche
    -0.43
     berikutnya
    -0.43
     malah
    -0.43
    POSITIVE LOGITS
    CloseOperation
    0.81
     مشين
    0.75
    ("")]
    0.72
    MLLoader
    0.71
    UnknownFields
    0.71
    invokeLater
    0.68
    enderror
    0.67
    audiovisuel
    0.67
    setVerticalGroup
    0.66
     Otherwise
    0.66
    Act Density 0.218%

    No Known Activations