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

    Neuronpedia

    INDEX
    Explanations

    data related to analysis and measurements, particularly in scientific or medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     was
    -0.91
     is
    -0.81
     has
    -0.72
     istnieje
    -0.65
     znajduje
    -0.64
     isn
    -0.63
     wordt
    -0.63
     zależy
    -0.57
     έχει
    -0.56
     occurs
    -0.56
    POSITIVE LOGITS
     were
    2.39
    Were
    1.68
     Were
    1.53
    were
    1.51
     WERE
    1.32
     waren
    1.23
     weren
    1.22
     были
    1.19
     voltak
    1.16
     byli
    1.15
    Act Density 1.070%

    No Known Activations