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

    Neuronpedia

    INDEX
    Explanations

    phrases and terminology related to academic publications and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enas
    -0.15
    æĺ¨
    -0.14
    omore
    -0.14
    czy
    -0.14
    paren
    -0.14
     Global
    -0.14
     Dreams
    -0.14
     Yesterday
    -0.14
     latest
    -0.14
    bjerg
    -0.14
    POSITIVE LOGITS
    197
    0.20
    198
    0.20
    196
    0.19
     USSR
    0.18
    ï¼ĪæĺŃåĴĮ
    0.17
     Ð¡Ð¡Ð¡Ðł
    0.16
    195
    0.16
     Soviet
    0.15
     tehdy
    0.15
    ifax
    0.14
    Act Density 1.159%

    No Known Activations