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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to individuals or entities whose characteristics or actions are being discussed

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

    whose followed by descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.36
     biela
    -0.35
    TestId
    -0.34
    Cordialement
    -0.34
     cucharadita
    -0.34
     Dingen
    -0.33
    GIF
    -0.31
     setId
    -0.30
     bruto
    -0.30
    them
    -0.30
    POSITIVE LOGITS
     Whose
    0.82
    Whose
    0.81
     whose
    0.79
    whose
    0.74
     ModelExpression
    0.71
     own
    0.66
     egne
    0.65
    ConstraintMaker
    0.64
    ftagPool
    0.60
     whom
    0.60
    Act Density 0.010%

    No Known Activations