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

    Neuronpedia

    INDEX
    Explanations

    references to quantities and their descriptions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vaar
    -0.52
     quæ
    -0.52
     huom
    -0.52
     Wohnen
    -0.52
     MCT
    -0.51
    ⓧ
    -0.51
     XK
    -0.51
     Audiodateien
    -0.49
     traccia
    -0.49
    erencia
    -0.49
    POSITIVE LOGITS
     piled
    0.71
    expandindo
    0.69
    Tembelea
    0.62
     piles
    0.60
     piling
    0.57
     innumerable
    0.57
    arraycopy
    0.57
    ngdoc
    0.57
    Chham
    0.56
    tomation
    0.56
    Act Density 0.046%

    No Known Activations