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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters, contracts, agreements, and requests

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    scape
    -0.64
    issance
    -0.58
     Virus
    -0.56
     predicament
    -0.55
     disturbance
    -0.55
     Cabin
    -0.55
     situation
    -0.54
    ression
    -0.53
    nea
    -0.53
     descriptor
    -0.52
    POSITIVE LOGITS
    poons
    1.16
     ranging
    1.16
     totaling
    1.14
     gal
    1.11
    pring
    1.05
    hots
    1.01
    uggest
    1.01
    ourcing
    0.98
    omething
    0.97
    hips
    0.94
    Act Density 0.552%

    No Known Activations