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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or qualifications involving "and" or "but"

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

    preceding relative pronouns (which, that, who)

    np_acts-logits-general · gemini-2.0-flash

    relative clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.67
    lapsingToolbar
    -0.56
     %}
    -0.55
    Extinguishing
    -0.54
    ąc
    -0.54
    warted
    -0.52
    ))))))))
    -0.51
    SharedDtor
    -0.51
    qtype
    -0.50
    felder
    -0.49
    POSITIVE LOGITS
     which
    2.28
     whose
    2.11
    whose
    1.86
    which
    1.81
     who
    1.78
     cuya
    1.60
     cuyo
    1.58
     cuyas
    1.58
     WHICH
    1.57
     Whose
    1.57
    Act Density 0.323%

    No Known Activations