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

    Neuronpedia

    INDEX
    Explanations

    numerical values and data related to standards or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongo
    -0.18
    nore
    -0.14
    inz
    -0.14
     Rek
    -0.13
     Curtain
    -0.13
    xis
    -0.13
    uchar
    -0.13
    277
    -0.13
    hou
    -0.13
    /package
    -0.13
    POSITIVE LOGITS
     æ¾
    0.15
    yclic
    0.14
    swers
    0.14
    ãģ£ãģ¡
    0.14
    .FC
    0.14
    ÑĸÑĶ
    0.13
     зм
    0.13
    circle
    0.13
    enny
    0.13
    blas
    0.13
    Act Density 0.034%

    No Known Activations