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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal and political activities or discussions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal proceedings or governmental processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mathemat
    -0.73
     popup
    -0.71
     reproduction
    -0.70
     whiff
    -0.70
     disadvant
    -0.67
     imitation
    -0.67
     reprodu
    -0.67
     readings
    -0.66
     fortun
    -0.65
     adaptation
    -0.65
    POSITIVE LOGITS
    ï¸ı
    1.01
    taboola
    0.89
    ATH
    0.87
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.85
    VICE
    0.83
    SHIP
    0.83
    Department
    0.81
    ·
    0.79
    éĩ
    0.77
    ħ
    0.77
    Act Density 0.562%

    No Known Activations