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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and relationships involving "who," "whom," and associated phrases

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

    whom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    -0.34
    is
    -0.32
     the
    -0.31
    S
    -0.31
     la
    -0.31
    d
    -0.31
     itself
    -0.30
     this
    -0.30
     This
    -0.30
    It
    -0.29
    POSITIVE LOGITS
    whom
    0.90
    rungsseite
    0.85
     queſta
    0.84
    ⟬
    0.84
    parsedMessage
    0.83
    jsonwebtoken
    0.82
     whom
    0.82
    featureID
    0.79
    ロウィン
    0.75
    Whom
    0.75
    Act Density 0.037%

    No Known Activations