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

    Neuronpedia

    INDEX
    Explanations

    references to academic titles and positions within universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¹īà¸Ńย
    -0.15
    cxx
    -0.15
    ISTA
    -0.14
    PCA
    -0.14
     çĿ
    -0.14
    dos
    -0.14
    arrant
    -0.14
    reu
    -0.14
    erge
    -0.14
    ÑĤÑĥ
    -0.14
    POSITIVE LOGITS
     Discipline
    0.28
     Curt
    0.27
     UNS
    0.27
     ARC
    0.25
     discipline
    0.23
     Mon
    0.22
     HDR
    0.21
    ARC
    0.21
     Murdoch
    0.20
     Griffith
    0.19
    Act Density 0.054%

    No Known Activations