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

    Neuronpedia

    INDEX
    Explanations

    patterns of letters 'up' followed by another letter, with increasing activation for longer patterns starting with 'up'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Ryder
    -0.85
    Ban
    -0.85
    inav
    -0.84
    Marie
    -0.83
    ÃŃn
    -0.83
    76561
    -0.80
    vest
    -0.78
    Interstitial
    -0.77
    ieth
    -0.73
    720
    -0.73
    POSITIVE LOGITS
    £ı
    0.80
    zhou
    0.79
    agall
    0.76
    gorith
    0.76
     machinery
    0.74
     Chimera
    0.69
    perty
    0.69
    worms
    0.68
     fit
    0.66
     Orion
    0.66
    Act Density 0.021%

    No Known Activations