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

    Neuronpedia

    INDEX
    Explanations

    references to collective groups or total quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Trend
    -0.65
     Sack
    -0.63
    assembly
    -0.62
     Caption
    -0.61
    gee
    -0.60
    istant
    -0.59
     newcomer
    -0.59
     Hort
    -0.59
    rift
    -0.57
     assail
    -0.56
    POSITIVE LOGITS
    been
    1.16
     been
    0.99
    ayed
    0.99
    ocated
    0.94
    owed
    0.89
     kinds
    0.88
     sorts
    0.87
     undergone
    0.85
    igator
    0.84
     gotten
    0.83
    Act Density 0.015%

    No Known Activations