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

    Neuronpedia

    INDEX
    Explanations

    references to time, particularly the concept of "last year" or related temporal events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kast
    -0.64
     Buk
    -0.61
    DebuggerNonUser
    -0.60
    mocha
    -0.60
     Firth
    -0.59
    rinfo
    -0.57
    ształ
    -0.57
     Kirkwood
    -0.56
    aurora
    -0.56
     kang
    -0.55
    POSITIVE LOGITS
     Paglinawan
    0.67
     fjor
    0.61
     night
    0.56
    сылкі
    0.54
    حوالہ
    0.52
    ionales
    0.50
     atap
    0.49
     continúas
    0.49
     kveld
    0.48
    гипет
    0.48
    Act Density 0.100%

    No Known Activations