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

    Neuronpedia

    INDEX
    Explanations

    nouns related to entities and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hus
    -0.15
     Erotik
    -0.15
    usaha
    -0.14
    enville
    -0.14
    hu
    -0.14
    een
    -0.14
    /ion
    -0.14
    etter
    -0.13
    jr
    -0.13
     Calder
    -0.13
    POSITIVE LOGITS
     Guy
    0.16
    Guy
    0.15
     responsible
    0.15
    norm
    0.14
    .synthetic
    0.14
    ordes
    0.14
     Append
    0.14
    nem
    0.14
     Responsible
    0.14
    411
    0.13
    Act Density 0.135%

    No Known Activations