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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of 'inclusion' or 'being included'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "in" followed by relative pronouns or prepositions

    np_acts-logits-general · gemini-2.0-flash

    in + context-setting phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.92
     itſelf
    -0.91
    RegressionTest
    -0.84
     themſelves
    -0.81
     myſelf
    -0.81
     Theſe
    -0.79
     Monfieur
    -0.78
    AsUp
    -0.78
     Jefus
    -0.77
     Baillargeon
    -0.76
    POSITIVE LOGITS
     which
    1.15
     including
    0.85
     albeit
    0.80
    which
    0.78
     although
    0.76
     especially
    0.75
     whose
    0.74
     cioè
    0.73
     cuyo
    0.70
     whom
    0.70
    Act Density 0.316%

    No Known Activations