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

    Neuronpedia

    INDEX
    Explanations

    terms related to derivation and sources in academic or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marcell
    -0.70
    ofon
    -0.67
     Zon
    -0.67
     Zell
    -0.65
    ZON
    -0.65
     Jank
    -0.63
     plomb
    -0.63
    timeZone
    -0.62
    xon
    -0.62
     Wonder
    -0.62
    POSITIVE LOGITS
     Derived
    1.04
     derive
    0.96
     derived
    0.95
    derived
    0.90
     derives
    0.86
     Erfurt
    0.85
     Burnet
    0.82
    InjectAttribute
    0.81
    VIAF
    0.81
     SEDS
    0.81
    Act Density 0.136%

    No Known Activations