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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating chronological sequence or time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Yesterday
    -0.20
     Yesterday
    -0.19
    esterday
    -0.18
     yesterday
    -0.18
     hôm
    -0.16
    ché
    -0.16
    ä»Ĭ
    -0.15
    æĺ¨
    -0.15
    argin
    -0.15
    usk
    -0.15
    POSITIVE LOGITS
     after
    0.30
     during
    0.29
     During
    0.25
     After
    0.25
    During
    0.23
     upon
    0.22
    After
    0.22
    during
    0.21
     while
    0.20
     durante
    0.20
    Act Density 0.100%

    No Known Activations