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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "just" in various contexts

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

    introducing statements with "just"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <=",
    -0.47
     nonUne
    -0.42
    탤
    -0.41
    äksi
    -0.40
     diver
    -0.40
    AutoField
    -0.39
     feld
    -0.38
    dataclass
    -0.38
    tracks
    -0.38
    起來
    -0.38
    POSITIVE LOGITS
    kloped
    0.54
     just
    0.54
    OGND
    0.54
    just
    0.52
    ReusableCell
    0.50
     biß
    0.48
    всегда
    0.47
     mengingatkan
    0.47
    SBATCH
    0.46
     always
    0.46
    Act Density 0.016%

    No Known Activations