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

    Neuronpedia

    INDEX
    Explanations

    positive descriptors related to beauty, quality, or value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pNet
    -0.16
    umont
    -0.15
     Morrow
    -0.15
    leh
    -0.14
    _WARNINGS
    -0.14
    ered
    -0.13
     Jensen
    -0.13
     =
    -0.13
    -0.13
     Prem
    -0.13
    POSITIVE LOGITS
    uchs
    0.17
    aight
    0.16
    lund
    0.14
    iece
    0.14
     Piet
    0.14
    /XML
    0.14
     Ãľn
    0.13
    Bounding
    0.13
    fea
    0.13
    estination
    0.13
    Act Density 0.260%

    No Known Activations