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

    Neuronpedia

    INDEX
    Explanations

    statements that introduce reasoning or causality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.85
    fjspx
    -0.79
    routeProvider
    -0.76
    TagHelpers
    -0.75
    MLLoader
    -0.73
     FontWeight
    -0.71
    randomUUID
    -0.71
    WritableDatabase
    -0.70
    SwingConstants
    -0.69
     Nestor
    -0.69
    POSITIVE LOGITS
    Because
    2.92
     Because
    2.83
     because
    2.75
    because
    2.73
     BECAUSE
    2.60
     porque
    2.19
    ECAUSE
    2.11
     Porque
    1.99
     perché
    1.95
    Porque
    1.94
    Act Density 0.106%

    No Known Activations