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

    Neuronpedia

    INDEX
    Explanations

    specific numerical identifiers or references, particularly in the context of structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     humour
    -0.19
     Pension
    -0.16
     neighbour
    -0.16
     colourful
    -0.15
     harbour
    -0.15
     neighbours
    -0.15
    avour
    -0.15
     Medieval
    -0.14
     Humph
    -0.14
    ycz
    -0.14
    POSITIVE LOGITS
     conversion
    0.24
     Conversion
    0.20
    conversion
    0.20
     Exodus
    0.20
     purity
    0.20
    Conversion
    0.20
     conversions
    0.19
     Ariel
    0.19
     therapy
    0.18
     repar
    0.18
    Act Density 0.006%

    No Known Activations