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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate management or administrative aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aft
    -0.16
    öh
    -0.16
    engin
    -0.16
    æ£ļ
    -0.15
    .toDouble
    -0.15
    rouch
    -0.15
    oller
    -0.14
    ugi
    -0.14
    .toFloat
    -0.14
    (ARG
    -0.14
    POSITIVE LOGITS
    aben
    0.17
    vu
    0.17
    acle
    0.14
     KromÄĽ
    0.14
    iyas
    0.14
     mans
    0.14
    еÑĢÑĥ
    0.14
    æ±ī
    0.14
    æĢģ
    0.13
    ledi
    0.13
    Act Density 0.126%

    No Known Activations