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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and evaluations of products and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawn
    -0.16
     Dysfunction
    -0.16
    /dist
    -0.15
    RIES
    -0.15
     aggrav
    -0.14
     unle
    -0.14
    retch
    -0.14
    olls
    -0.14
    ucker
    -0.14
     worsening
    -0.14
    POSITIVE LOGITS
     ham
    0.28
     dog
    0.26
     mar
    0.26
     torpedo
    0.26
     dent
    0.25
     tank
    0.24
     d
    0.24
     dash
    0.23
    ham
    0.22
     submar
    0.21
    Act Density 0.167%

    No Known Activations