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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing equality or equal importance

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -0.97
     uſed
    -0.82
     Jefus
    -0.82
     оригіналу
    -0.79
    úgó
    -0.78
    ValueStyle
    -0.76
     Theſe
    -0.76
     iſt
    -0.75
    leyball
    -0.75
    owulf
    -0.74
    POSITIVE LOGITS
     equally
    0.75
     Equally
    0.65
    lez
    0.59
    rami
    0.56
     igualmente
    0.53
     matters
    0.51
     пы
    0.51
    '
    0.51
    equ
    0.50
    iterator
    0.49
    Act Density 0.014%

    No Known Activations