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

    Neuronpedia

    INDEX
    Explanations

    significant nouns and phrases related to events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Derfor
    -0.74
     when
    -0.70
     därför
    -0.64
    Ведь
    -0.61
     therefore
    -0.59
     everytime
    -0.58
     derfor
    -0.58
    when
    -0.58
     Deshalb
    -0.57
     whenever
    -0.57
    POSITIVE LOGITS
    Elsewhere
    1.47
     Elsewhere
    1.37
     Meanwhile
    1.07
    Meanwhile
    1.02
    Rounding
    1.01
     elsewhere
    1.00
     meanwhile
    0.94
    Also
    0.92
     Also
    0.89
     Among
    0.88
    Act Density 0.134%

    No Known Activations