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

    Neuronpedia

    INDEX
    Explanations

    phrases related to implementing changes or initiatives

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Evil
    -0.78
    lus
    -0.73
    Fuck
    -0.69
     Zionist
    -0.69
     hatred
    -0.68
     Rupert
    -0.67
     Rebellion
    -0.65
     Evil
    -0.65
     treason
    -0.65
    Appearances
    -0.64
    POSITIVE LOGITS
     prioritize
    0.96
     inspected
    0.94
     instituted
    0.93
     audits
    0.93
     redesigned
    0.92
     evaluated
    0.92
     phased
    0.92
     backlog
    0.91
     reimb
    0.91
     inspect
    0.90
    Act Density 0.460%

    No Known Activations