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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 'd'

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

    would or had

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     varandra
    -0.53
     frågan
    -0.52
    ("."
    -0.48
     allmän
    -0.47
     defaultstate
    -0.46
     areia
    -0.43
     verksam
    -0.43
     døde
    -0.43
     currentValue
    -0.42
     problemet
    -0.42
    POSITIVE LOGITS
     Would
    0.74
    Would
    0.74
     would
    0.71
    would
    0.68
     been
    0.67
    phol
    0.67
     be
    0.65
     had
    0.64
    uld
    0.64
     prolly
    0.64
    Act Density 0.009%

    No Known Activations