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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the naming or designation of entities and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     >=",
    -0.80
    MigrationBuilder
    -0.72
    });*/
    -0.65
     <>",
    -0.65
     للمعارف
    -0.64
    __':
    -0.63
     дописавши
    -0.62
    aarrggbb
    -0.60
    })*/
    -0.60
    ]--;
    -0.59
    POSITIVE LOGITS
     idées
    0.50
     appunto
    0.49
    cientos
    0.48
     fermée
    0.48
     ICollection
    0.48
     Mangel
    0.48
     ujednoznacz
    0.47
    nsf
    0.46
    LEA
    0.46
     reserving
    0.46
    Act Density 0.234%

    No Known Activations