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

    Neuronpedia

    INDEX
    Explanations

    instances of time-related phrases or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelves
    -0.92
     Cæsar
    -0.90
    ſelf
    -0.89
     leſs
    -0.89
     myſelf
    -0.87
     themſelves
    -0.86
     faſt
    -0.84
     pleaſure
    -0.83
     houſe
    -0.83
     Shakspeare
    -0.81
    POSITIVE LOGITS
     he
    0.76
     when
    0.67
    зулта
    0.64
     the
    0.63
     Référence
    0.63
     after
    0.61
     then
    0.60
     I
    0.59
     it
    0.58
     बाद
    0.58
    Act Density 0.199%

    No Known Activations