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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intenance
    -0.53
    reszcie
    -0.53
    örté
    -0.50
    ManagedBean
    -0.50
    årige
    -0.48
    +#+#
    -0.48
    Skocz
    -0.47
    antity
    -0.47
     endregion
    -0.47
    ண்டும்
    -0.46
    POSITIVE LOGITS
    RUnlock
    0.75
    httphttps
    0.72
     CreateTagHelper
    0.68
     iNdEx
    0.65
    msgTypes
    0.65
     becauſe
    0.64
     ſever
    0.63
    RegressionTest
    0.63
    <eos>
    0.61
     Theſe
    0.61
    Act Density 0.208%

    No Known Activations