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

    Neuronpedia

    INDEX
    Explanations

    pronouns, particularly those referring to male and female characters

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

    "he" at the beginning of a sentence or clause

    np_acts-logits-general · gemini-2.0-flash

    he followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vspace
    -0.38
    όμε
    -0.36
     Natural
    -0.36
     in
    -0.35
    ंदु
    -0.32
    tic
    -0.32
    vskip
    -0.32
    KindOfClass
    -0.32
     Common
    -0.32
     odd
    -0.31
    POSITIVE LOGITS
    He
    1.02
     Ellos
    1.00
    she
    1.00
    THEY
    0.98
    they
    0.95
    She
    0.95
     ſhe
    0.95
     he
    0.94
    They
    0.94
    Mereka
    0.94
    Act Density 0.311%

    No Known Activations