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

    Neuronpedia

    INDEX
    Explanations

    words associated with decay or repetitiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.16
    YO
    -0.16
    ean
    -0.16
    yas
    -0.16
    sdale
    -0.15
    314
    -0.14
    Tank
    -0.14
    703
    -0.14
    Ñıз
    -0.14
     pa
    -0.14
    POSITIVE LOGITS
    alis
    0.16
    ãĥijãĥ³
    0.16
    .scalablytyped
    0.15
     Recon
    0.14
    .weixin
    0.14
    attice
    0.14
    izin
    0.14
    loor
    0.14
    gov
    0.14
     recon
    0.13
    Act Density 0.031%

    No Known Activations