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

    Neuronpedia

    INDEX
    Explanations

    phrases related to past experiences or changes over time

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    edIn
    -0.69
     Continued
    -0.62
    raw
    -0.61
    medi
    -0.60
    response
    -0.60
    ceptive
    -0.59
    OGR
    -0.59
     outcomes
    -0.58
     fails
    -0.58
    assembly
    -0.57
    POSITIVE LOGITS
     haunt
    0.90
     joke
    0.88
     look
    0.82
     enjoy
    0.81
     be
    0.80
     populate
    0.80
     resemble
    0.79
     treat
    0.78
     stomp
    0.78
     dominate
    0.76
    Act Density 0.063%

    No Known Activations