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

    Neuronpedia

    INDEX
    Explanations

    references to opposition or dissent in political or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.78
     sapiens
    -0.61
    artament
    -0.59
    GeoNames
    -0.54
     gainera
    -0.51
    ренко
    -0.49
    oneph
    -0.48
     Prato
    -0.48
    getJSONArray
    -0.47
    𝘮
    -0.47
    POSITIVE LOGITS
     opposition
    3.29
    opposition
    2.98
    Opposition
    2.79
     Opposition
    2.70
     oppose
    2.48
     opposes
    2.36
     opposed
    2.27
     oppos
    2.21
     oposición
    2.09
     opposing
    2.06
    Act Density 0.099%

    No Known Activations