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

    Neuronpedia

    INDEX
    Explanations

    references to specific events or reports involving people or places

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    SPONSORED
    -1.15
    ĵĺ
    -1.04
     compr
    -1.01
    externalActionCode
    -0.98
     livest
    -0.95
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.94
     distingu
    -0.94
     ende
    -0.93
     withd
    -0.93
     tremend
    -0.92
    POSITIVE LOGITS
    ting
    2.14
    TING
    2.08
    ters
    1.98
    ts
    1.73
    ted
    1.69
    ter
    1.57
    rics
    1.56
    tering
    1.48
    aneous
    1.47
    nik
    1.44
    Act Density 1.173%

    No Known Activations