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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uds
    -0.15
     ratings
    -0.15
     rating
    -0.14
     Fauc
    -0.14
     solid
    -0.14
     Amen
    -0.13
     Disclaimer
    -0.13
     Indigenous
    -0.13
    AGMA
    -0.13
    920
    -0.13
    POSITIVE LOGITS
    .assertThat
    0.26
     assertThat
    0.19
     Matchers
    0.18
    Matchers
    0.17
    ï¸
    0.16
    Matcher
    0.16
    holm
    0.16
    presso
    0.16
    ģµ
    0.15
     matcher
    0.15
    Act Density 0.005%

    No Known Activations