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

    Neuronpedia

    INDEX
    Explanations

    terms related to guiding or instructing others and innovation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.89
    /**
    -0.71
     propose
    -0.65
    ⓧ
    -0.64
    
    -0.63
     began
    -0.63
     started
    -0.62
     also
    -0.62
     spoke
    -0.61
     begin
    -0.59
    POSITIVE LOGITS
     saar
    1.33
     lele
    1.31
     jaya
    1.30
     maksi
    1.29
     gomma
    1.28
     maroc
    1.28
     ceramica
    1.27
     autunno
    1.27
     levis
    1.27
     Juf
    1.27
    Act Density 0.520%

    No Known Activations