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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and references to individuals in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __':
    -0.45
    قایناق‌لار
    -0.40
    orcid
    -0.39
     Audiodateien
    -0.39
    "},
    -0.38
    
    -0.36
    おきます
    -0.36
    %;
    -0.36
    __":
    -0.36
    相反
    -0.36
    POSITIVE LOGITS
     تضيفلها
    0.54
     pleaſure
    0.52
    GOTREF
    0.51
     OMITBAD
    0.51
    دانشنامهٔ
    0.49
    ReusableCell
    0.48
    verifyException
    0.48
    AnimationsModule
    0.47
     ſtate
    0.47
     houſe
    0.47
    Act Density 0.192%

    No Known Activations