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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and the structure of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     And
    -0.22
    And
    -0.19
     Plus
    -0.18
    exemple
    -0.16
     indeed
    -0.15
    Plus
    -0.15
    inand
    -0.15
    oder
    -0.14
     Which
    -0.14
    pecially
    -0.14
    POSITIVE LOGITS
     although
    0.24
    Although
    0.21
     Although
    0.21
    Because
    0.20
    although
    0.20
     except
    0.19
     Because
    0.18
     since
    0.18
     apart
    0.17
     besides
    0.17
    Act Density 0.314%

    No Known Activations