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

    Neuronpedia

    INDEX
    Explanations

    expressions of moral or ethical guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     without
    -0.42
    hup
    -0.39
     WITHOUT
    -0.39
     alemanes
    -0.38
    udia
    -0.37
    /?
    -0.37
     czemu
    -0.37
     tưởng
    -0.37
    如果不
    -0.36
    GeneratedValue
    -0.36
    POSITIVE LOGITS
     nor
    3.40
    nor
    2.67
     Nor
    2.66
    Nor
    2.61
     Tampoco
    2.10
    而是
    2.00
     NOR
    1.93
     sondern
    1.89
     neither
    1.85
     بلکه
    1.82
    Act Density 0.476%

    No Known Activations