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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to measurements or data in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.66
    Connecting
    -0.57
    chakra
    -0.55
    connecting
    -0.52
    unking
    -0.51
     looking
    -0.50
    atka
    -0.50
     taking
    -0.49
    iring
    -0.48
     joining
    -0.48
    POSITIVE LOGITS
    rungsseite
    0.67
    ografija
    0.66
     frattempo
    0.61
    InstrumentedTest
    0.61
     Rela
    0.58
    URIComponent
    0.57
    aluz
    0.57
    Xna
    0.56
     apnea
    0.56
    orexia
    0.56
    Act Density 0.826%

    No Known Activations