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

    Neuronpedia

    INDEX
    Explanations

    references to time, specifically the word "Later" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.78
    %)$
    -0.77
     ​​
    -0.76
     McDonough
    -0.75
     AssemblyTitle
    -0.73
     &___
    -0.71
    ]--;
    -0.69
    offsetof
    -0.68
    brett
    -0.67
     ویکی‌پدیای
    -0.65
    POSITIVE LOGITS
    later
    1.28
     LATER
    1.21
     later
    1.21
     Later
    1.20
    Later
    1.18
     späteren
    1.00
    sequent
    0.92
     afterward
    0.89
     baller
    0.88
     Depois
    0.88
    Act Density 0.064%

    No Known Activations