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

    Neuronpedia

    INDEX
    Explanations

    titles of films and entertainment-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _MODIFIED
    -0.15
    236
    -0.15
    hani
    -0.15
    Ïģει
    -0.15
    antage
    -0.14
    inis
    -0.14
    ahren
    -0.14
    555
    -0.14
    .toolbox
    -0.14
    onal
    -0.14
    POSITIVE LOGITS
    iens
    0.18
    ilon
    0.15
     Carson
    0.14
    Liked
    0.14
    AYS
    0.14
     statute
    0.14
    illi
    0.14
    Äįan
    0.14
    nak
    0.14
     unp
    0.13
    Act Density 0.003%

    No Known Activations