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

    Neuronpedia

    INDEX
    Explanations

    instances of brackets and mathematical notations or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    offsetof
    -0.67
    withIdentifier
    -0.61
    SuppressMessage
    -0.61
    下载附件
    -0.58
    CrossOrigin
    -0.58
     newBuilder
    -0.58
    }*/
    -0.57
    urlencoded
    -0.57
    penup
    -0.55
    ிக்க
    -0.55
    POSITIVE LOGITS
    ="
    0.62
    มาะ
    0.62
     colspan
    0.61
    =".$
    0.59
    =".
    0.55
    Билгалдахарш
    0.55
    sca
    0.54
    DEAR
    0.54
    ]=="
    0.52
    =").
    0.51
    Act Density 0.012%

    No Known Activations