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

    Neuronpedia

    INDEX
    Explanations

    phrases related to size and ranking in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.12
    ^(@)
    -1.11
     itſelf
    -1.08
     myſelf
    -1.08
     Theſe
    -1.07
    )");
    -1.06
     Diſ
    -1.04
    IsContent
    -1.03
    AccessorTable
    -1.01
     tfsi
    -1.01
    POSITIVE LOGITS
    ,
    0.73
     (
    0.62
    .
    0.61
    <eos>
    0.53
     
    0.51
     [
    0.48
    <b>
    0.47
     Mo
    0.47
    ↵↵
    0.46
      
    0.45
    Act Density 0.221%

    No Known Activations