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

    Neuronpedia

    INDEX
    Explanations

    terms related to governmental policies and societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Heard
    -0.20
     Holdings
    -0.19
     Hack
    -0.18
    Hunter
    -0.18
     Hunter
    -0.17
     Helm
    -0.17
     Homework
    -0.16
     Handler
    -0.16
    Hom
    -0.16
     Harmon
    -0.16
    POSITIVE LOGITS
     h
    1.65
    .h
    0.90
    $h
    0.82
    =h
    0.80
    *h
    0.75
    (h
    0.73
    [h
    0.73
    h
    0.73
    :h
    0.71
    Âłh
    0.68
    Act Density 0.601%

    No Known Activations