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

    Neuronpedia

    INDEX
    Explanations

    temporal indicators or phrases that denote time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.73
     unſ
    -0.63
     Reſ
    -0.61
     myſelf
    -0.57
     raiſ
    -0.57
     deſt
    -0.57
     faſt
    -0.56
     صوتيه
    -0.55
     fubject
    -0.55
     neceſſ
    -0.54
    POSITIVE LOGITS
     gdyż
    0.78
     because
    0.76
     ponieważ
    0.73
     poiché
    0.70
    because
    0.66
    Because
    0.65
     eftersom
    0.65
    因为
    0.65
     Porque
    0.65
     Because
    0.64
    Act Density 0.279%

    No Known Activations