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

    Neuronpedia

    INDEX
    Explanations

    discussions related to sentences and sentence structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fleste
    -0.72
     Warburton
    -0.69
    icoot
    -0.68
     aussieht
    -0.67
    alamus
    -0.66
    dolu
    -0.65
    لاثة
    -0.64
    eryllium
    -0.62
     nicio
    -0.61
    rinfo
    -0.61
    POSITIVE LOGITS
     sentences
    1.54
     sentence
    1.49
     Sentence
    1.44
    sentences
    1.28
     Sentences
    1.26
    Sentence
    1.25
    sentence
    1.21
     frase
    0.99
     paragraph
    0.90
     phrase
    0.89
    Act Density 0.140%

    No Known Activations