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

    Neuronpedia

    INDEX
    Explanations

    emotions or interactions involving physical touch and expressions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fuf
    -2.05
     accla
    -2.04
     strick
    -2.00
     embra
    -2.00
     reluct
    -2.00
     inev
    -1.97
     increa
    -1.96
     emphat
    -1.94
     guarante
    -1.93
     affor
    -1.90
    POSITIVE LOGITS
    <bos>
    0.68
    .
    0.64
    <eos>
    0.64
    invokeLater
    0.61
     again
    0.61
    єра
    0.60
    stereotype
    0.60
     under
    0.59
     bune
    0.59
    евна
    0.59
    Act Density 0.204%

    No Known Activations