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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fraudulent schemes or illegal activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    inas
    -0.70
    ãģĹ
    -0.67
    Nob
    -0.66
    parts
    -0.64
    lake
    -0.64
    Flo
    -0.64
     Lutheran
    -0.61
     Sie
    -0.61
    bors
    -0.61
    ãģķ
    -0.61
    POSITIVE LOGITS
     schemes
    1.10
     scheme
    1.02
     devised
    0.94
    eers
    0.91
    etary
    0.81
    mable
    0.80
    eering
    0.79
    ĸļ
    0.79
    matic
    0.79
    matically
    0.78
    Act Density 0.020%

    No Known Activations