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

    Neuronpedia

    INDEX
    Explanations

    references to spiritual teachings or allegories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¹īว
    -0.17
    stride
    -0.17
    å®Ļ
    -0.16
    ÑĤаÑħ
    -0.15
    æ°
    -0.15
    .metro
    -0.15
    antal
    -0.14
    é¡
    -0.14
    sembly
    -0.14
    ÑĥлÑıÑĢ
    -0.14
    POSITIVE LOGITS
     Sentinel
    0.17
    Daemon
    0.16
     (
    0.15
    enburg
    0.15
     Sent
    0.15
    ahat
    0.15
     Chan
    0.14
     Cent
    0.14
     Giles
    0.14
    d
    0.14
    Act Density 0.048%

    No Known Activations