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

    Neuronpedia

    INDEX
    Explanations

    requests or directives in the context of filling forms or agreeing to terms and policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.82
    oÄŁan
    -0.70
    kus
    -0.69
    Gil
    -0.68
    arson
    -0.64
    pocket
    -0.64
     Tycoon
    -0.61
    Dick
    -0.61
     sensations
    -0.60
    Station
    -0.60
    POSITIVE LOGITS
     disclaimer
    1.19
     agreement
    1.06
     Agreement
    1.04
     clauses
    1.03
     disclaim
    1.00
     stip
    0.99
     confidentiality
    0.99
     agreements
    0.97
    claimer
    0.97
     forbids
    0.94
    Act Density 0.247%

    No Known Activations