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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or social issues and consequences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal issues and personal rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £ı
    -0.91
    ãĤ©
    -0.74
    ãĤ¤ãĥĪ
    -0.70
    NRS
    -0.69
     mosqu
    -0.68
    ACTED
    -0.68
    CSS
    -0.65
     earthqu
    -0.65
    ç«
    -0.64
    Recomm
    -0.63
    POSITIVE LOGITS
     inmates
    0.92
     among
    0.85
     recipients
    0.85
     amongst
    0.82
     bestowed
    0.80
     claimants
    0.79
     belonging
    0.79
     individuals
    0.79
     students
    0.79
     Haku
    0.78
    Act Density 0.510%

    No Known Activations