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

    Neuronpedia

    INDEX
    Explanations

    terms related to delays, errors, and inconsistencies in processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vil
    -0.17
    enze
    -0.16
    eres
    -0.15
    berger
    -0.15
    igon
    -0.15
     aggression
    -0.15
    _guard
    -0.15
    etros
    -0.15
    argent
    -0.15
    νια
    -0.15
    POSITIVE LOGITS
    ging
    0.48
    ged
    0.45
    gy
    0.43
    gers
    0.41
    gings
    0.35
    gle
    0.34
    gie
    0.33
    gin
    0.33
    ger
    0.32
    gs
    0.30
    Act Density 0.725%

    No Known Activations