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

    Neuronpedia

    INDEX
    Explanations

    information related to arrests and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to legal issues and arrests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Franch
    -0.71
     SAN
    -0.71
     Haku
    -0.66
    theless
    -0.66
     Koh
    -0.65
     photoc
    -0.65
     Bak
    -0.64
     Strauss
    -0.64
     Princ
    -0.63
     Izan
    -0.63
    POSITIVE LOGITS
    under
    0.88
    ombat
    0.87
    anco
    0.87
    obar
    0.85
    vernment
    0.80
    opard
    0.78
    rates
    0.78
    well
    0.76
    asion
    0.75
    arist
    0.75
    Act Density 0.139%

    No Known Activations