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

    Neuronpedia

    INDEX
    Explanations

    references to specific groups of people

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

    "those" followed by a relative pronoun

    np_acts-logits-general · gemini-2.0-flash

    those who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ecap
    -0.67
     varandra
    -0.63
    IndentedString
    -0.62
     nuages
    -0.59
     wikipagina
    -0.57
     każde
    -0.54
    these
    -0.54
    SerializedSize
    -0.52
    addContainerGap
    -0.52
    Cormack
    -0.52
    POSITIVE LOGITS
     who
    1.73
     whom
    1.11
     whose
    1.00
    who
    0.98
    whose
    0.79
     involved
    0.79
    whom
    0.79
    Whose
    0.76
     Who
    0.73
     that
    0.73
    Act Density 0.116%

    No Known Activations