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

    Neuronpedia

    INDEX
    Explanations

    keywords related to legal settings or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to courthouses or legal settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umar
    -0.84
    hy
    -0.75
    olls
    -0.75
    lust
    -0.75
    ku
    -0.73
    growth
    -0.73
    hell
    -0.72
    sen
    -0.72
    loss
    -0.71
    lihood
    -0.71
    POSITIVE LOGITS
     courthouse
    1.37
    thouse
    1.10
     plaza
    0.88
     chapel
    0.85
     Pengu
    0.84
     courtyard
    0.83
     clerk
    0.83
     gates
    0.82
     courtroom
    0.81
     Plaza
    0.80
    Act Density 0.002%

    No Known Activations