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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Jennifer."

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

    the name Jennifer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ragion
    -0.45
     Horne
    -0.41
     escala
    -0.39
    στό
    -0.39
     Begründung
    -0.38
     Gründe
    -0.38
    scale
    -0.38
    sd
    -0.37
     regola
    -0.37
     Beale
    -0.37
    POSITIVE LOGITS
     Jennifer
    1.80
    Jennifer
    1.66
     jennifer
    1.45
    jennifer
    1.38
     Jenn
    0.93
    IFER
    0.87
    ennifer
    0.87
    Jenn
    0.82
    iffer
    0.72
     Gén
    0.67
    Act Density 0.001%

    No Known Activations