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

    Neuronpedia

    INDEX
    Explanations

    statements related to security issues or political actions

    oai_token-act-pair · gpt-3.5-turbo

    direct quotes and reported speech in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bourbon
    -0.76
    Utah
    -0.76
     Spokane
    -0.75
     Dwight
    -0.75
     Pebble
    -0.74
    Ohio
    -0.74
     Madison
    -0.74
     NASCAR
    -0.74
     dime
    -0.74
     honoring
    -0.73
    POSITIVE LOGITS
     Kaf
    1.04
     Mahm
    0.93
    beit
    0.92
    istani
    0.91
     Rai
    0.91
     NGO
    0.90
    ÅŁ
    0.89
    afa
    0.89
    edi
    0.89
     Riy
    0.88
    Act Density 0.718%

    No Known Activations