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

    Neuronpedia

    INDEX
    Explanations

    patterns related to grammar and language structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bench
    -0.16
     Leadership
    -0.16
    translated
    -0.15
     Stephan
    -0.15
    Translate
    -0.14
    á»Ŀi
    -0.14
    Leaders
    -0.14
    legate
    -0.14
     synonyms
    -0.14
     translate
    -0.13
    POSITIVE LOGITS
    omor
    0.17
     advertis
    0.17
     speakers
    0.17
     speech
    0.17
     Humb
    0.16
    utters
    0.15
     realization
    0.15
    saldo
    0.15
     surpr
    0.15
     книж
    0.14
    Act Density 0.044%

    No Known Activations