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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms indicating quotations or references

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -1.31
     raiſ
    -1.15
     himſelf
    -1.14
     Efq
    -1.13
    ſelf
    -1.13
     photolibrary
    -1.13
     houſe
    -1.13
     itſelf
    -1.10
     purpoſe
    -1.08
     uſed
    -1.08
    POSITIVE LOGITS
    <eos>
    0.68
     
    0.59
    AddHtmlAttribute
    0.57
     *
    0.57
     (
    0.56
     '
    0.53
    .
    0.52
     the
    0.51
    ↵↵
    0.50
     "
    0.50
    Act Density 0.007%

    No Known Activations