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

    Neuronpedia

    INDEX
    Explanations

    elements or variables related to statistics and measurements in the context of analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     colourful
    -0.17
     initialised
    -0.16
    Colour
    -0.16
    _colour
    -0.15
     Colour
    -0.15
     behavioural
    -0.15
    UNUSED
    -0.15
     flavours
    -0.15
     favourable
    -0.15
     colour
    -0.15
    POSITIVE LOGITS
     revision
    0.23
    Revision
    0.22
     writing
    0.20
     workshop
    0.20
     writer
    0.20
     writers
    0.20
     provisional
    0.20
     revisions
    0.19
     Revision
    0.19
     fucked
    0.18
    Act Density 0.024%

    No Known Activations