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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their roles or qualities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Edit
    -0.81
    events
    -0.77
    fn
    -0.77
    anism
    -0.76
    mares
    -0.74
    attacks
    -0.72
    advertisement
    -0.71
    uden
    -0.70
    views
    -0.69
    encies
    -0.69
    POSITIVE LOGITS
     fixture
    1.07
     descendant
    1.06
     proud
    1.06
     staunch
    1.06
     member
    1.04
     devout
    1.02
     believer
    1.01
     supporter
    1.00
     prolific
    0.98
     lifelong
    0.97
    Act Density 0.190%

    No Known Activations