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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical or scientific concepts of correspondence or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rinfo
    -0.57
    :✨
    -0.56
     صوتيه
    -0.45
    NUMX
    -0.44
     doInBackground
    -0.43
     merak
    -0.43
    ercises
    -0.43
    assertIn
    -0.42
    Tikang
    -0.42
    isGrid
    -0.41
    POSITIVE LOGITS
    Corresponding
    0.91
     corresponding
    0.91
     Corresponding
    0.88
     correspond
    0.87
    corresponding
    0.86
     corresponds
    0.76
     Correspond
    0.75
     associated
    0.74
    对应
    0.71
     corresponded
    0.70
    Act Density 1.663%

    No Known Activations