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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "until" or "till."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Hrsg
    -0.60
     (
    -0.52
     ‘
    -0.50
     li
    -0.50
     dor
    -0.49
    ,
    -0.49
    }}^
    -0.49
    :
    -0.48
    ंप
    -0.48
    ’
    -0.46
    POSITIVE LOGITS
     nahilalakip
    1.13
     itſelf
    1.09
     myſelf
    1.08
     raiſ
    1.05
     beginnetje
    1.02
    ContentAsync
    1.00
     Monfieur
    1.00
     poffible
    0.99
     themſelves
    0.98
     ―――――
    0.97
    Act Density 0.008%

    No Known Activations