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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the potential for benefits or properties related to substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QMetaType
    -0.91
    PYX
    -0.72
     Wiktionnaire
    -0.71
    IVEREF
    -0.70
     ویکی‌پدیا
    -0.69
    szön
    -0.69
    mbh
    -0.65
    IntoConstraints
    -0.65
    tafel
    -0.65
     iNdEx
    -0.64
    POSITIVE LOGITS
    se
    1.46
    fe
    0.71
    comp
    0.65
    sed
    0.63
     digitais
    0.59
     deliberately
    0.54
    SE
    0.53
    reszcie
    0.53
     sauvages
    0.52
     purposefully
    0.52
    Act Density 0.070%

    No Known Activations