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

    Neuronpedia

    INDEX
    Explanations

    patterns resembling codes or numerical sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æľĽ
    -0.17
    12
    -0.17
    २०
    -0.16
    asant
    -0.16
    ï¼ijï¼IJ
    -0.15
    १à¥
    -0.15
    10
    -0.15
    11
    -0.15
    cket
    -0.15
    १९
    -0.15
    POSITIVE LOGITS
     tslint
    0.15
     Hamp
    0.15
    bite
    0.14
     bic
    0.14
    8
    0.14
     [âĢ¦]↵↵
    0.13
    otel
    0.13
    9
    0.13
    Ħ
    0.13
    راÙĨÙĩ
    0.13
    Act Density 0.154%

    No Known Activations