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

    Neuronpedia

    INDEX
    Explanations

    instances of character interactions and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     varandra
    -0.59
    Autoritní
    -0.56
    esis
    -0.52
     scale
    -0.46
     verksam
    -0.46
    odly
    -0.46
     constitución
    -0.46
     volet
    -0.46
    schrank
    -0.45
    nicity
    -0.45
    POSITIVE LOGITS
     Савезне
    0.78
    RenderAtEndOf
    0.72
    ########.
    0.64
     CreateTagHelper
    0.61
    EndContext
    0.59
     mumbled
    0.58
     transférez
    0.57
     eventdata
    0.56
    UnusedPrivate
    0.56
    ksikon
    0.55
    Act Density 0.269%

    No Known Activations