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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating repetition or the act of redoing something

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

    recommend again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ouncements
    -0.54
    RTEE
    -0.45
    лтемелер
    -0.44
     تضيفلها
    -0.43
    tences
    -0.43
     ConstraintSet
    -0.41
     seta
    -0.40
    propy
    -0.40
     davidson
    -0.40
    })`
    -0.40
    POSITIVE LOGITS
     gdyby
    0.47
    Diweddarwch
    0.43
     recommand
    0.43
    tvguidetime
    0.39
    migrationBuilder
    0.37
     jederzeit
    0.37
    anything
    0.37
    SequentialGroup
    0.36
     gladly
    0.36
     recomendo
    0.35
    Act Density 0.004%

    No Known Activations