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

    Neuronpedia

    INDEX
    Explanations

    technical code terms and instructions

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols that denote various aspects of text formatting or coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Page
    -1.04
    Bul
    -0.85
    Value
    -0.84
    Stage
    -0.83
    Args
    -0.82
    ingo
    -0.82
    WAR
    -0.81
    Round
    -0.81
    lette
    -0.81
    Lear
    -0.80
    POSITIVE LOGITS
     ult
    0.78
    assetsadobe
    0.76
     segregation
    0.75
     nod
    0.74
     pione
    0.73
     guiActiveUn
    0.73
     ful
    0.71
     foul
    0.70
     indirect
    0.70
     creat
    0.70
    Act Density 0.376%

    No Known Activations