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

    Neuronpedia

    INDEX
    Explanations

    non-specific or low-activation texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    caref
    -0.52
    àng
    -0.51
    aken
    -0.49
    ÁB
    -0.49
     gł
    -0.49
     lang
    -0.49
    entrySet
    -0.48
    gin
    -0.47
    Externé
    -0.47
    schul
    -0.47
    POSITIVE LOGITS
    /*
    0.83
     kasarigan
    0.81
     resourceCulture
    0.79
    <bos>
    0.75
    ])));
    0.74
    ]));
    0.74
     jurídica
    0.71
    "]));
    0.69
    "]}
    0.69
    
    0.68
    Act Density 0.217%

    No Known Activations