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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce or define concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reportWebVitals
    -0.54
     Viter
    -0.49
     traseiro
    -0.47
     fprintf
    -0.46
    örté
    -0.45
     meski
    -0.45
     يتيمه
    -0.45
    inerja
    -0.44
    despite
    -0.44
     guère
    -0.44
    POSITIVE LOGITS
     called
    1.21
     CALLED
    1.18
    called
    1.15
     Called
    1.10
    Called
    1.09
     llamado
    0.94
    叫做
    0.93
     nicknamed
    0.93
    appelle
    0.90
     dubbed
    0.90
    Act Density 0.186%

    No Known Activations