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

    Neuronpedia

    INDEX
    Explanations

    words related to time periods, particularly decades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    房
    -0.74
     la
    -0.69
    e
    -0.68
    y
    -0.66
    er
    -0.65
    a
    -0.65
    sam
    -0.65
    Angelina
    -0.65
    心
    -0.64
    tab
    -0.64
    POSITIVE LOGITS
    jectures
    1.10
    etheless
    1.08
     Eſ
    1.04
    theless
    1.02
    ſelf
    0.98
    Cyfeiriadau
    0.96
     myſelf
    0.96
    0.96
     ſeveral
    0.95
     whoſe
    0.94
    Act Density 0.122%

    No Known Activations