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

    Neuronpedia

    INDEX
    Explanations

    phrases that begin with "As" to signal comparisons or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     evidenced
    -0.19
    etter
    -0.18
    fcn
    -0.17
    emean
    -0.17
    ungan
    -0.15
    inders
    -0.14
    ients
    -0.14
    Äħż
    -0.14
    ieu
    -0.14
    atti
    -0.14
    POSITIVE LOGITS
     such
    0.31
    such
    0.23
     result
    0.22
     Such
    0.22
    Such
    0.21
     luck
    0.20
    ynchronous
    0.20
     SUCH
    0.19
     consequence
    0.18
    pects
    0.18
    Act Density 0.059%

    No Known Activations