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

    Neuronpedia

    INDEX
    Explanations

    capitalized proper nouns and unique identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jeb
    -0.16
    tir
    -0.16
    tement
    -0.15
    unts
    -0.14
     Axel
    -0.14
    iling
    -0.14
    omed
    -0.14
    arg
    -0.14
    isyon
    -0.14
     Pep
    -0.14
    POSITIVE LOGITS
    ely
    0.27
    ivel
    0.26
    ű
    0.21
    ester
    0.21
    indent
    0.19
    indh
    0.19
    ELY
    0.19
    enny
    0.18
    ert
    0.18
    esters
    0.18
    Act Density 0.001%

    No Known Activations