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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating obligations or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Served
    -0.68
    IndentedString
    -0.68
    Naissance
    -0.66
    いかが
    -0.62
     själ
    -0.61
    Üdv
    -0.60
    shadowOpacity
    -0.59
    WireFormatLite
    -0.59
     урна
    -0.58
    yped
    -0.58
    POSITIVE LOGITS
    UVWXYZ
    0.62
     Pelleg
    0.57
    ǒ
    0.55
     Audiodateien
    0.55
    μμ
    0.55
     Persson
    0.55
    ılıyor
    0.52
    ‍♀️
    0.51
    litch
    0.49
     deal
    0.49
    Act Density 0.123%

    No Known Activations