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

    Neuronpedia

    INDEX
    Explanations

    sequences that represent string concatenation and output formatting in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.48
     rendent
    -0.47
     présentés
    -0.46
    不够
    -0.45
    יוחד
    -0.44
     hâte
    -0.43
     användas
    -0.43
     rapides
    -0.43
     aussitôt
    -0.43
    encana
    -0.42
    POSITIVE LOGITS
    tvguidetime
    0.98
    0.87
    verwijspagina
    0.80
     "<<
    0.75
     consultato
    0.74
    livejournal
    0.69
    ViewImports
    0.68
    codegen
    0.67
    ubscribe
    0.65
    теристика
    0.64
    Act Density 0.156%

    No Known Activations