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

    Neuronpedia

    INDEX
    Explanations

    the word "which" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lexikon
    -0.59
    @[+][
    -0.53
     pulumi
    -0.50
    timewa
    -0.50
    nyttet
    -0.50
    culate
    -0.50
    assar
    -0.49
    ZZA
    -0.48
    Gew
    -0.47
    iddhar
    -0.47
    POSITIVE LOGITS
     wiederum
    0.89
     incidentally
    0.88
     admittedly
    0.86
     unfortunately
    0.83
     кстати
    0.80
     tentunya
    0.79
     thankfully
    0.79
     itself
    0.76
     malheureusement
    0.76
     is
    0.75
    Act Density 0.310%

    No Known Activations