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

    Neuronpedia

    INDEX
    Explanations

    various occurrences of the word ''yes''

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    bage
    -0.78
    perial
    -0.74
    RAW
    -0.73
    inese
    -0.65
     rall
    -0.62
    MpServer
    -0.61
    versions
    -0.59
    actionDate
    -0.59
    agascar
    -0.58
    recated
    -0.57
    POSITIVE LOGITS
    terday
    1.94
    hua
    0.83
     sir
    0.82
    TER
    0.74
     indeed
    0.71
     matter
    0.66
    hhhh
    0.66
    hur
    0.65
     Pryor
    0.65
    eed
    0.65
    Act Density 0.050%

    No Known Activations