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

    Neuronpedia

    INDEX
    Explanations

    terms that introduce elaborative or explanatory phrases

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

    introducing specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    发表于
    -0.42
    Биография
    -0.41
     pan
    -0.39
    UrlResolution
    -0.37
    riek
    -0.34
     sce
    -0.34
    aol
    -0.33
     CAT
    -0.32
     Fah
    -0.32
     flu
    -0.32
    POSITIVE LOGITS
     nemlig
    0.82
     namely
    0.82
     Namely
    0.78
    namely
    0.77
     yaitu
    0.73
     nämlich
    0.73
     namelijk
    0.72
     cioè
    0.71
     iaitu
    0.70
    yaitu
    0.69
    Act Density 0.159%

    No Known Activations