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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transferring authority or control from one entity to another

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    odox
    -0.72
    SL
    -0.70
    LI
    -0.70
    xtap
    -0.69
    NECT
    -0.68
    rities
    -0.64
    anwhile
    -0.62
    AH
    -0.62
    GW
    -0.62
    Si
    -0.62
    POSITIVE LOGITS
     custody
    0.80
     reins
    0.77
    PsyNetMessage
    0.72
     keys
    0.71
     stewards
    0.70
     ownership
    0.70
     scraps
    0.68
    leased
    0.68
     responsibility
    0.67
     receipts
    0.66
    Act Density 0.031%

    No Known Activations