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

    Neuronpedia

    INDEX
    Explanations

    words related to progress or advancement

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to programs or projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬
    -0.79
    âĸ¬âĸ¬
    -0.74
     Logged
    -0.68
    ++++++++++++++++
    -0.66
     dere
    -0.65
    rawdownloadcloneembedreportprint
    -0.63
     BDS
    -0.63
    pora
    -0.62
    ````
    -0.60
    terday
    -0.60
    POSITIVE LOGITS
    ersen
    1.06
    nostic
    0.90
    ester
    0.89
    resso
    0.89
    rade
    0.87
    lator
    0.84
    solete
    0.83
    acing
    0.80
    illac
    0.79
    eah
    0.78
    Act Density 0.031%

    No Known Activations