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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical computer tasks and processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     earthqu
    -0.64
     respected
    -0.60
     Plaza
    -0.58
     SEM
    -0.58
     redes
    -0.57
     compelling
    -0.56
     msec
    -0.56
     entrenched
    -0.56
     arsen
    -0.55
     powerful
    -0.55
    POSITIVE LOGITS
    lihood
    1.13
    _-_
    1.05
    tenance
    1.04
    terday
    1.03
    _
    1.00
    etheless
    0.99
    /)
    0.95
    self
    0.95
    /,
    0.93
    __
    0.90
    Act Density 0.162%

    No Known Activations