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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "interesting" used in various contexts

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

    introducing something interesting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ӕ
    -0.55
     kepem
    -0.50
     Godhead
    -0.49
    Cyfeiriadau
    -0.49
    ﷺ
    -0.48
     Gown
    -0.46
    таратура
    -0.45
    TypedDataSet
    -0.44
     Majefty
    -0.44
    Билгалдахарш
    -0.44
    POSITIVE LOGITS
     interesting
    1.86
    interesting
    1.81
     Interesting
    1.75
    Interesting
    1.73
     interesante
    1.38
     interessante
    1.36
     intéressante
    1.30
     zajíma
    1.27
     intéressant
    1.25
     interessantes
    1.25
    Act Density 0.012%

    No Known Activations