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

    Neuronpedia

    INDEX
    Explanations

    references to the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uga
    -0.15
     min
    -0.14
     outright
    -0.14
     {:.
    -0.13
    lig
    -0.13
     знаком
    -0.13
    ter
    -0.13
     vice
    -0.13
     resident
    -0.13
     tight
    -0.13
    POSITIVE LOGITS
    ->
    0.38
    ->_
    0.32
    ->___
    0.32
     ->
    0.22
    ::$
    0.21
    ->$
    0.21
    ->__
    0.21
    -&
    0.20
    ->{
    0.20
    ->{$
    0.19
    Act Density 0.004%

    No Known Activations