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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting related to data structures and coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hakim
    -0.63
    hermes
    -0.56
     Dune
    -0.56
     hermes
    -0.56
     Ches
    -0.55
     Rasa
    -0.54
     Sah
    -0.54
     Vera
    -0.54
     Willy
    -0.52
     Wra
    -0.51
    POSITIVE LOGITS
    .[
    1.16
    "[
    1.14
     '[
    1.13
    ("[
    1.10
    '[
    1.09
    ?[
    1.09
    ,[
    1.07
    ="[
    1.06
     "[
    1.06
    :[
    1.06
    Act Density 1.708%

    No Known Activations