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

    Neuronpedia

    INDEX
    Explanations

    strings and their associated formatting in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.30
    Personendaten
    -1.24
    )");
    -1.21
    $")
    -1.18
     myſelf
    -1.16
     betweenstory
    -1.16
    ."));
    -1.15
    ")));
    -1.13
     itſelf
    -1.13
    تقاوى
    -1.11
    POSITIVE LOGITS
     -
    0.86
     |
    0.76
     –
    0.75
     /
    0.69
     (
    0.66
     —
    0.64
     --
    0.61
     ||
    0.61
    ,
    0.59
     •
    0.58
    Act Density 0.341%

    No Known Activations