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

    Neuronpedia

    INDEX
    Explanations

    temporal expressions indicating specific timeframes

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

    late, early, end of periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     händer
    -0.49
     sécher
    -0.37
    exprimer
    -0.37
    SEGUIR
    -0.36
    inscrire
    -0.35
    occuper
    -0.34
    intéress
    -0.34
     énergé
    -0.34
     dég
    -0.34
     vectorielles
    -0.33
    POSITIVE LOGITS
     mid
    0.77
    月中
    0.69
     early
    0.65
    月中旬
    0.64
    mid
    0.64
    early
    0.59
     late
    0.58
    late
    0.58
    月初
    0.58
    Mid
    0.57
    Act Density 0.043%

    No Known Activations