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

    Neuronpedia

    INDEX
    Explanations

    references to legal actions and outcomes, particularly regarding convictions and criminal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suits
    -0.15
    setattr
    -0.15
    ftar
    -0.14
     arrest
    -0.14
    uli
    -0.14
     yere
    -0.14
    889
    -0.14
     viol
    -0.14
    agate
    -0.14
     Kiss
    -0.14
    POSITIVE LOGITS
     motive
    0.20
    ishi
    0.15
    _PTR
    0.15
    .execution
    0.15
    rik
    0.15
    Tro
    0.15
    rial
    0.15
     Coverage
    0.15
    )(*
    0.14
    моÑĤ
    0.14
    Act Density 0.081%

    No Known Activations