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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and formal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     �
    -0.74
    <?
    -0.69
     ’
    -0.61
     …
    -0.60
    <s>
    -0.59
    #{
    -0.58
    AspNet
    -0.58
     ____
    -0.56
     _____
    -0.56
     #{
    -0.55
    POSITIVE LOGITS
     $\$
    0.78
    .\\
    0.76
    \[
    0.73
    存于互联网档案馆
    0.70
    ).\\
    0.69
    ftagPool
    0.68
     \&
    0.66
     للاسماء
    0.66
    awtextra
    0.65
     $=$
    0.65
    Act Density 0.222%

    No Known Activations