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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "always."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obble
    -0.17
    женÑĮ
    -0.16
    ulet
    -0.15
    915
    -0.15
     Fran
    -0.14
    лон
    -0.14
    aml
    -0.14
     undef
    -0.14
    給
    -0.14
    .
    -0.13
    POSITIVE LOGITS
    rpc
    0.16
    åѸéĻ¢
    0.16
    udit
    0.16
    ifiable
    0.15
    ãĥ¼ãĤº
    0.15
    .scalablytyped
    0.15
    annel
    0.14
    .ArgumentParser
    0.14
    ENCHMARK
    0.14
    åѦéĻ¢
    0.14
    Act Density 0.079%

    No Known Activations