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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government actions targeting specific groups or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to government actions against civil liberties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Centauri
    -0.76
    tein
    -0.66
     Construct
    -0.65
    orgetown
    -0.64
    ndra
    -0.64
    pec
    -0.64
    esthetic
    -0.62
    izable
    -0.62
     Upton
    -0.62
     Lakes
    -0.61
    POSITIVE LOGITS
     crackdown
    1.19
     sweeps
    0.77
     clamp
    0.75
    ãĤ¸
    0.72
     enforcement
    0.71
     targeting
    0.71
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    0.70
    alos
    0.70
    Operation
    0.70
     regimes
    0.69
    Act Density 0.016%

    No Known Activations