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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluations of success and failure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    any one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.51
     상세
    -0.50
    verwijspagina
    -0.50
    Personendaten
    -0.48
    tawesome
    -0.45
    헌
    -0.45
    riwal
    -0.44
    клопе
    -0.43
    principalColumn
    -0.43
    urlpatterns
    -0.43
    POSITIVE LOGITS
     anyone
    0.50
    anyone
    0.47
     ANYONE
    0.47
     unmet
    0.44
     anybody
    0.41
     anywhere
    0.41
     unoccupied
    0.41
    httphttps
    0.41
     unsatisfied
    0.40
    findOne
    0.39
    Act Density 0.020%

    No Known Activations