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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authorship or attribution in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes after "by"

    np_acts-logits-general · gemini-2.0-flash

    identifying authorship or source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mybatisplus
    -0.90
    onViewCreated
    -0.80
    TagMode
    -0.80
     Мексичка
    -0.80
    InjectAttribute
    -0.79
    tagHelperRunner
    -0.76
    UnsafeEnabled
    -0.75
    #![
    -0.75
    ScopeManager
    -0.73
     ་་
    -0.73
    POSITIVE LOGITS
    :
    1.16
     @
    0.84
     Dr
    0.73
     J
    0.73
     /
    0.70
     :
    0.68
    @
    0.68
     The
    0.66
     admin
    0.63
     Unknown
    0.63
    Act Density 0.161%

    No Known Activations