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

    Neuronpedia

    INDEX
    Explanations

    phrases related to past habits or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hentet
    -0.74
     ſtate
    -0.62
     habet
    -0.60
    atás
    -0.60
     purpoſe
    -0.59
     houſe
    -0.59
     perſon
    -0.59
     individualism
    -0.58
     mxArray
    -0.57
     perfons
    -0.57
    POSITIVE LOGITS
     früher
    0.95
     formerly
    0.91
     Formerly
    0.87
    昔
    0.86
     раньше
    0.85
     ago
    0.83
    Formerly
    0.83
    исленность
    0.82
    adays
    0.79
     vroeger
    0.79
    Act Density 0.069%

    No Known Activations