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

    Neuronpedia

    INDEX
    Explanations

    keywords related to computer commands and prompts

    oai_token-act-pair · gpt-3.5-turbo

    references to command-line operations and prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥª
    -0.80
     Ukrain
    -0.74
    abouts
    -0.65
     Beir
    -0.64
    verning
    -0.64
     Econom
    -0.63
    اÙĦ
    -0.63
     Sect
    -0.61
     Torn
    -0.61
    akening
    -0.60
    POSITIVE LOGITS
     prompt
    1.26
    line
    1.11
     line
    1.10
     Prompt
    0.99
    Line
    0.97
     substitution
    0.93
     injection
    0.92
     invocation
    0.89
     syntax
    0.88
    LINE
    0.87
    Act Density 0.049%

    No Known Activations