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

    Neuronpedia

    INDEX
    Explanations

    code snippets involving function declarations and invocations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carrington
    -0.55
    vesen
    -0.55
     astore
    -0.54
    witter
    -0.51
     Ause
    -0.50
     ")[
    -0.49
     régi
    -0.48
     Bert
    -0.48
    iah
    -0.48
    ModelAdmin
    -0.48
    POSITIVE LOGITS
    (()
    1.82
    (()=>{
    1.17
    (()=>
    1.14
    +#+
    1.10
     تضيفلها
    0.93
    ſelf
    0.91
     myſelf
    0.88
     (()
    0.86
     NLI
    0.84
    Javadoc
    0.84
    Act Density 0.007%

    No Known Activations