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

    Neuronpedia

    INDEX
    Explanations

    ellipses or repeated patterns in sequences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ldots
    -0.74
     Mee
    -0.66
    Eug
    -0.64
     Yvette
    -0.63
    Yaw
    -0.63
    {}\
    -0.61
    Chl
    -0.59
     en
    -0.57
    -
    -0.57
    alla
    -0.57
    POSITIVE LOGITS
     Roskov
    1.09
    enterOuterAlt
    1.02
     Eſ
    1.00
     ainfi
    0.95
    antMatchers
    0.93
     myſelf
    0.91
     Efq
    0.89
     Wiseman
    0.88
     fevere
    0.84
     bershka
    0.84
    Act Density 0.003%

    No Known Activations