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

    Neuronpedia

    INDEX
    Explanations

    strings of text preceded by specific words, likely related to programming code or data structures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "String" and variations along with other data types and structures in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vic
    -0.67
     Predator
    -0.66
     moder
    -0.65
     ethics
    -0.64
     dro
    -0.64
     Kens
    -0.63
     AMA
    -0.63
     cann
    -0.63
     Dak
    -0.63
     OC
    -0.63
    POSITIVE LOGITS
    String
    3.56
    string
    2.22
     String
    2.13
    Integer
    1.71
    STR
    1.64
    strings
    1.61
     string
    1.59
    Array
    1.51
     strings
    1.47
    Str
    1.39
    Act Density 0.018%

    No Known Activations