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

    Neuronpedia

    INDEX
    Explanations

    references to "people" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    'gc
    -0.19
     Rum
    -0.16
    iks
    -0.15
    options
    -0.15
    /sm
    -0.15
     ucwords
    -0.14
    ooks
    -0.14
    ertools
    -0.14
    supports
    -0.14
    森
    -0.14
    POSITIVE LOGITS
    izza
    0.15
    Pin
    0.15
     Gene
    0.15
    orate
    0.15
     Pin
    0.14
    mae
    0.14
    784
    0.14
    ª
    0.14
    fare
    0.14
    ridge
    0.14
    Act Density 0.106%

    No Known Activations