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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical structures and locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukunft
    -0.66
    <bos>
    -0.65
    tierrez
    -0.63
     inconce
    -0.63
     Nguy
    -0.58
     unspeak
    -0.54
     coiff
    -0.54
     redire
    -0.54
     unwarran
    -0.53
    zanas
    -0.51
    POSITIVE LOGITS
     écout
    0.71
     accompagne
    0.62
     vécu
    0.59
     choisis
    0.58
     empêche
    0.57
     répon
    0.56
     réunis
    0.56
     soigne
    0.55
     terminée
    0.55
     thick
    0.54
    Act Density 0.220%

    No Known Activations