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

    Neuronpedia

    INDEX
    Explanations

    terms related to brands and trademarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berger
    -0.18
    ourcem
    -0.17
    thur
    -0.17
    ncia
    -0.17
    elijk
    -0.16
    ipline
    -0.14
    avage
    -0.14
    umber
    -0.13
     Beer
    -0.13
    _ALIAS
    -0.13
    POSITIVE LOGITS
    uliar
    0.27
     pe
    0.21
    bles
    0.20
    (pe
    0.19
     Pe
    0.19
    ople
    0.18
    -pe
    0.17
    anggan
    0.17
    haps
    0.16
    .pe
    0.16
    Act Density 0.024%

    No Known Activations