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

    Neuronpedia

    INDEX
    Explanations

    titles and affiliations of academic professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilog
    -0.16
     DISPATCH
    -0.15
    umber
    -0.15
    dos
    -0.15
    aines
    -0.14
    ISTA
    -0.14
    -cert
    -0.14
    ovich
    -0.14
     Railroad
    -0.14
    erge
    -0.14
    POSITIVE LOGITS
     Discipline
    0.28
     UNS
    0.27
     HDR
    0.27
     ARC
    0.24
     Curt
    0.24
     Mon
    0.22
     discipline
    0.22
     Griffith
    0.21
     Faculty
    0.21
    ARC
    0.21
    Act Density 0.051%

    No Known Activations