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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "in" and its variations as indicators of location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Thurs
    -0.19
     Tomorrow
    -0.18
     Mondays
    -0.18
     Fridays
    -0.18
    IFn
    -0.18
     tomorrow
    -0.18
    NEXT
    -0.17
    Tomorrow
    -0.17
     Saturdays
    -0.17
     Tues
    -0.16
    POSITIVE LOGITS
     late
    0.76
    late
    0.59
     early
    0.56
     Late
    0.52
     mid
    0.49
    Late
    0.47
    early
    0.43
    mid
    0.38
     Early
    0.32
     fall
    0.31
    Act Density 0.119%

    No Known Activations