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

    Neuronpedia

    INDEX
    Explanations

    terms related to significant findings or important results in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     significantly
    -0.63
     dramatically
    -0.59
     sharply
    -0.59
    slightly
    -0.58
     Савезне
    -0.57
     drastically
    -0.56
    significantly
    -0.56
    (!__
    -0.56
     slightly
    -0.56
    dras
    -0.55
    POSITIVE LOGITS
     amounts
    0.81
     amount
    0.77
     differences
    0.75
     Unterschied
    0.71
     difference
    0.71
    amounts
    0.69
    ItemBackground
    0.67
    amount
    0.67
     inroads
    0.66
     increase
    0.66
    Act Density 0.545%

    No Known Activations