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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or comparisons, particularly focusing on the concept of "between."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enfans
    -0.68
     auroit
    -0.60
    mstyle
    -0.56
     avoient
    -0.53
     pleaſure
    -0.53
     feroit
    -0.50
     pouvoit
    -0.50
     âmes
    -0.49
    ſelf
    -0.48
     épaules
    -0.48
    POSITIVE LOGITS
     between
    1.71
    Between
    1.56
    between
    1.55
     Between
    1.55
    BETWEEN
    1.38
     BETWEEN
    1.35
     между
    1.34
     zwischen
    1.33
     між
    1.24
     tussen
    1.20
    Act Density 0.101%

    No Known Activations