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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional situations and emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.61
     phosphat
    -0.47
    ValueGeneration
    -0.47
     Aufl
    -0.47
    ANZA
    -0.47
     fallu
    -0.47
     voici
    -0.47
    TITUDE
    -0.47
     retraite
    -0.46
    assword
    -0.45
    POSITIVE LOGITS
    __':
    0.66
    TagHelper
    0.64
    __':
    0.63
    InjectAttribute
    0.56
    ölker
    0.53
     cold
    0.52
     Océ
    0.52
    RegressionTest
    0.51
     eyelashes
    0.51
    webElement
    0.50
    Act Density 0.042%

    No Known Activations