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

    Neuronpedia

    INDEX
    Explanations

    references to conditions and qualities related to items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    matchCondition
    -0.71
     ostavi
    -0.66
    WebElementEntity
    -0.62
    Fordítás
    -0.61
     őket
    -0.60
    AnimationsModule
    -0.59
    ArgumentParser
    -0.58
     Grecs
    -0.58
     tasche
    -0.58
     pouvoirs
    -0.57
    POSITIVE LOGITS
     respectively
    1.04
     examples
    0.92
    respectively
    0.91
     etc
    0.87
     among
    0.80
     respectivamente
    0.79
     these
    0.78
    etc
    0.77
     những
    0.75
     things
    0.75
    Act Density 0.520%

    No Known Activations