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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds or scientific terms related to research and development

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.80
     cultiv
    -0.72
    staking
    -0.68
     FTA
    -0.63
    thood
    -0.63
    tails
    -0.61
     Vietnamese
    -0.59
     Ferr
    -0.59
    stall
    -0.58
    java
    -0.58
    POSITIVE LOGITS
    ewski
    1.26
    cz
    1.00
    ynski
    0.94
    ombie
    0.87
    immer
    0.87
    omp
    0.80
    zyk
    0.79
    ealous
    0.78
    cedented
    0.78
    inski
    0.74
    Act Density 0.034%

    No Known Activations