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

    Neuronpedia

    INDEX
    Explanations

    references to formal reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    engin
    -0.20
    кÑĥÑĢ
    -0.15
    usercontent
    -0.14
    жив
    -0.14
    bay
    -0.14
    ิว
    -0.14
    loha
    -0.14
     sucker
    -0.14
     suck
    -0.14
    ugins
    -0.13
    POSITIVE LOGITS
    oks
    0.16
    dependency
    0.15
     unst
    0.15
     dependency
    0.15
     ass
    0.15
    aks
    0.15
    olean
    0.15
    ecký
    0.14
     Fortune
    0.14
    vat
    0.14
    Act Density 0.003%

    No Known Activations