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

    Neuronpedia

    INDEX
    Explanations

    personal information or data

    oai_token-act-pair · gpt-3.5-turbo

    references to personal data and privacy issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -1.12
    LER
    -0.73
    GGGG
    -0.73
     âĶľ
    -0.72
    UMP
    -0.69
     Removal
    -0.69
    terday
    -0.68
    WER
    -0.67
    NESS
    -0.67
    owitz
    -0.66
    POSITIVE LOGITS
    ised
    1.13
    ized
    1.02
    ization
    1.00
    ities
    0.97
     belongings
    0.97
    izing
    0.97
    istic
    0.94
     pronouns
    0.91
    istically
    0.90
    izes
    0.89
    Act Density 0.019%

    No Known Activations