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

    Neuronpedia

    INDEX
    Explanations

    the word "in" and phrases emphasizing its usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     addition
    -0.18
     Addition
    -0.17
     whom
    -0.17
     cui
    -0.17
    Which
    -0.17
    which
    -0.16
    ixa
    -0.16
     which
    -0.16
    lesen
    -0.16
    quire
    -0.15
    POSITIVE LOGITS
     concert
    0.29
     stages
    0.26
     partnership
    0.23
     isolation
    0.23
    house
    0.23
     earnest
    0.22
     phases
    0.22
     pairs
    0.21
     parallel
    0.21
    -house
    0.21
    Act Density 0.242%

    No Known Activations