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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ger" with varying intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "ger" in various contexts and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unaffected
    -0.62
     rendered
    -0.62
     Ac
    -0.61
     limitless
    -0.59
     Vive
    -0.57
     unlikely
    -0.57
     00000000
    -0.56
     exempt
    -0.56
     Valiant
    -0.55
     Sacrament
    -0.54
    POSITIVE LOGITS
    ger
    4.50
    gers
    3.20
    GER
    2.51
    ging
    2.24
    ged
    2.06
    gered
    2.00
    gery
    1.80
    ges
    1.79
    gest
    1.67
    gement
    1.52
    Act Density 0.013%

    No Known Activations