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

    Neuronpedia

    INDEX
    Explanations

    financial or business-related terms or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     misunder
    -0.73
     swast
    -0.70
     decomp
    -0.69
     mathemat
    -0.67
     hurd
    -0.65
     Allied
    -0.65
     decom
    -0.65
     Berks
    -0.65
     democracy
    -0.64
     fragmentation
    -0.64
    POSITIVE LOGITS
    ï¸ı
    1.10
    tion
    0.99
    s
    0.98
    TION
    0.95
    shall
    0.93
    ski
    0.93
    ship
    0.92
    iversary
    0.90
    t
    0.87
    _.
    0.86
    Act Density 0.289%

    No Known Activations