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

    Neuronpedia

    INDEX
    Explanations

    people's names, particularly those related to legal or political contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    icles
    -0.46
    rx
    -0.43
    tails
    -0.42
    á½
    -0.40
    uate
    -0.40
    osc
    -0.40
    match
    -0.39
    UE
    -0.39
    sync
    -0.39
    icle
    -0.39
    POSITIVE LOGITS
     Wiggins
    0.56
     Manning
    0.56
     Bradley
    0.56
     Cooper
    0.47
     Sisters
    0.42
     Byrne
    0.41
     pigeon
    0.41
     Fir
    0.40
     McD
    0.40
     Kirst
    0.39
    Act Density 0.653%

    No Known Activations