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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "since" along with temporal phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himſelf
    -0.91
     Efq
    -0.87
     Chriſt
    -0.87
     myſelf
    -0.84
     themſelves
    -0.81
    oa̍t
    -0.79
    oredCriteria
    -0.78
     Monfieur
    -0.76
     Cæsar
    -0.74
     ſeveral
    -0.74
    POSITIVE LOGITS
    since
    0.99
     since
    0.97
    Since
    0.90
     Since
    0.90
     SINCE
    0.88
     the
    0.82
    Seit
    0.74
    Desde
    0.73
     Depuis
    0.68
     sinds
    0.66
    Act Density 0.054%

    No Known Activations