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

    Neuronpedia

    INDEX
    Explanations

    vertical bar characters in various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensement
    -0.63
    */)
    -0.58
    -0.58
     풍
    -0.57
     PUN
    -0.56
    ----------
    -0.55
    '")
    -0.54
    =").
    -0.54
    <0xF4>
    -0.53
    )))
    -0.53
    POSITIVE LOGITS
     |
    3.04
    |
    2.16
     $|
    2.11
    .|
    1.86
    }|
    1.84
     $|\
    1.78
    )|
    1.75
    "|
    1.75
     |\
    1.75
    $|
    1.72
    Act Density 0.098%

    No Known Activations