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

    Neuronpedia

    INDEX
    Explanations

    mathematical operators and expressions involving variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.82
     Monfieur
    -0.80
    InstrumentedTest
    -0.80
     étoient
    -0.76
     avoient
    -0.76
    الحياه
    -0.75
     feroit
    -0.75
     Majefty
    -0.75
     ſche
    -0.71
    Personensuche
    -0.70
    POSITIVE LOGITS
    edo
    0.48
     rien
    0.48
    itinéraire
    0.47
     
    0.47
     Rechnung
    0.47
     stří
    0.45
     ($
    0.45
    ↵↵
    0.44
     Bas
    0.43
    grano
    0.43
    Act Density 0.881%

    No Known Activations