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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and structural components within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    States
    -0.96
    STATES
    -0.86
     STATES
    -0.83
     myſelf
    -0.83
     faſt
    -0.82
    thâu
    -0.79
    states
    -0.79
    AnchorStyles
    -0.79
     fubject
    -0.77
     States
    -0.75
    POSITIVE LOGITS
     state
    0.47
     stated
    0.47
     sta
    0.47
     tat
    0.45
     stat
    0.40
     statt
    0.38
     государ
    0.34
    tat
    0.31
     ста
    0.30
     State
    0.29
    Act Density 0.310%

    No Known Activations