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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional phrases that indicate relationships between ideas or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    them
    -0.91
     THEM
    -0.80
    antaranya
    -0.78
    そして
    -0.77
     alebo
    -0.75
    หรือ
    -0.72
     Then
    -0.72
     или
    -0.71
    或
    -0.71
    herself
    -0.70
    POSITIVE LOGITS
     there
    1.50
     although
    1.48
     while
    1.47
     when
    1.45
     despite
    1.45
     since
    1.43
     if
    1.42
     unlike
    1.38
     after
    1.30
     during
    1.30
    Act Density 1.682%

    No Known Activations