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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical injury and medical treatment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     depic
    -1.31
     encomp
    -1.27
     Manufact
    -1.24
     »>
    -1.20
     ftu
    -1.20
     accla
    -1.20
     emphat
    -1.19
     pixabay
    -1.18
     fep
    -1.17
     véhic
    -1.16
    POSITIVE LOGITS
     twice
    1.22
     repeatedly
    1.11
     frequently
    1.09
     regularly
    1.06
     every
    0.98
    twice
    0.91
    frequently
    0.86
     occasionally
    0.85
     often
    0.85
     periodically
    0.84
    Act Density 0.364%

    No Known Activations