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

    Neuronpedia

    INDEX
    Explanations

    patterns of usage related to the phrase "used to" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themſelves
    -0.70
    addPreferredGap
    -0.63
     ſtate
    -0.63
     himſelf
    -0.62
    windowFixed
    -0.62
    ſelves
    -0.62
     ſmall
    -0.60
    Hentet
    -0.60
    oustics
    -0.56
     ſever
    -0.56
    POSITIVE LOGITS
     früher
    0.81
     раньше
    0.79
    昔
    0.73
     formerly
    0.72
     vroeger
    0.71
    เคย
    0.70
     pernah
    0.69
     Formerly
    0.68
    GraphicsUnit
    0.67
    исленность
    0.65
    Act Density 0.169%

    No Known Activations