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

    Neuronpedia

    INDEX
    Explanations

    terms related to electronic technology

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     heal
    -0.78
     gor
    -0.77
     healed
    -0.73
     plat
    -0.73
     worsen
    -0.73
     rav
    -0.72
     haunt
    -0.71
    %%%%
    -0.70
     sag
    -0.67
     scapego
    -0.67
    POSITIVE LOGITS
     Electronic
    3.84
     Electronics
    1.60
    Elect
    1.56
     EFF
    1.44
     Computer
    1.40
     EA
    1.26
     Electrical
    1.23
     Digital
    1.19
     Interactive
    1.18
     Telecommunications
    1.18
    Act Density 0.021%

    No Known Activations