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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing confusion or lack of understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.14
     jakarta
    -0.51
    ///**
    -0.47
     AppCompatTheme
    -0.47
    ensure
    -0.45
     pessi
    -0.44
     enri
    -0.44
    lineto
    -0.42
     hydrate
    -0.41
     inject
    -0.41
    POSITIVE LOGITS
     cajones
    0.72
    postolic
    0.72
     conclud
    0.66
     explanation
    0.65
    capulco
    0.65
     soggior
    0.64
     puzzling
    0.63
     sappi
    0.62
     hecta
    0.62
     fathoms
    0.62
    Act Density 0.315%

    No Known Activations