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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and their relations in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     THEN
    -0.18
     then
    -0.17
     themselves
    -0.16
     Then
    -0.16
    Then
    -0.16
     herself
    -0.15
     etc
    -0.15
     سپس
    -0.14
     himself
    -0.14
    .then
    -0.14
    POSITIVE LOGITS
     there
    0.30
     it
    0.30
    there
    0.24
     has
    0.23
     although
    0.22
     is
    0.21
     because
    0.20
     unless
    0.20
     while
    0.20
    has
    0.19
    Act Density 0.395%

    No Known Activations