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

    Neuronpedia

    INDEX
    Explanations

    references to programming elements and code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Reporting
    -0.08
    !!!!↵↵
    -0.08
    essen
    -0.08
     rall
    -0.08
     mastur
    -0.08
    Xã
    -0.08
     ↵↵
    -0.07
    âĢ¦.↵↵
    -0.07
    ãģĸ
    -0.07
     bordel
    -0.07
    POSITIVE LOGITS
    aga
    0.06
    ols
    0.06
    ield
    0.05
    ank
    0.05
    outh
    0.05
    _inode
    0.05
    /or
    0.05
    ih
    0.05
    yr
    0.05
    peater
    0.05
    Act Density 0.035%

    No Known Activations