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

    Neuronpedia

    INDEX
    Explanations

    words related to endings or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    words that end with the suffix "end" or "ending."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edom
    -0.78
    tery
    -0.69
    hee
    -0.68
    ppo
    -0.67
    tyard
    -0.66
    oda
    -0.64
    çİĭ
    -0.64
    onde
    -0.63
     Byrd
    -0.63
    zzi
    -0.62
    POSITIVE LOGITS
    lich
    0.83
    ENDED
    0.72
    ending
    0.70
    rils
    0.70
    ended
    0.69
    adoes
    0.69
    ragon
    0.68
    ends
    0.68
    LY
    0.64
    uality
    0.63
    Act Density 0.016%

    No Known Activations