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

    Neuronpedia

    INDEX
    Explanations

    academic references and citations in research articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    balleur
    -0.74
     BorderRadius
    -0.72
    Rüyada
    -0.72
     BoxFit
    -0.71
     لينك
    -0.68
    rungsseite
    -0.68
    awtextra
    -0.68
    GOTREF
    -0.68
    bkz
    -0.68
    audiovisuel
    -0.67
    POSITIVE LOGITS
    *,
    0.76
    †
    0.69
     Department
    0.65
     ${
    0.64
     †
    0.63
     *,
    0.63
    ,*
    0.60
    *
    0.60
    dagger
    0.57
    *;
    0.55
    Act Density 0.325%

    No Known Activations