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

    Neuronpedia

    INDEX
    Explanations

    references to historical cinematic elements or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AGENT
    -0.18
    stown
    -0.16
     Opt
    -0.16
     rumpe
    -0.16
    Und
    -0.15
    Dot
    -0.15
     Und
    -0.15
    ëĦ¤
    -0.15
     Fur
    -0.14
     Most
    -0.14
    POSITIVE LOGITS
     niet
    0.25
     va
    0.22
     ook
    0.22
     nau
    0.22
     wel
    0.21
     heel
    0.21
     veel
    0.21
     mind
    0.20
     som
    0.20
     sle
    0.20
    Act Density 0.065%

    No Known Activations