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

    Neuronpedia

    INDEX
    Explanations

    conjunctions that express contrast or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !”
    -1.79
    !’
    -1.76
    !),
    -1.65
    ↵
    -1.57
    <|outofrange|>
    -1.57
    ↵↵
    -1.57
    ↵
    -1.57
    -1.57
    ↵  âĢĥ
    -1.57
      ↵
    -1.57
    POSITIVE LOGITS
    inine
    1.84
    onset
    1.57
    WHM
    1.52
     \%
    1.50
    ondo
    1.47
    elic
    1.45
    CLUSION
    1.43
     protease
    1.42
    ortium
    1.41
    ausing
    1.37
    Act Density 0.001%

    No Known Activations