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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to phases and transitions in materials or chemical processes

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

    phase stabilization and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.46
    Rüyada
    -0.44
     britannique
    -0.42
    받
    -0.41
     scottish
    -0.41
     cuantas
    -0.40
     Escri
    -0.40
     cuánt
    -0.40
     australian
    -0.39
     الدولى
    -0.39
    POSITIVE LOGITS
     Phase
    1.32
    Phase
    1.32
     phase
    1.27
    phase
    1.20
     PHASE
    1.16
     phases
    1.11
     Phases
    1.08
    PHASE
    1.05
    phases
    1.00
    Phases
    0.99
    Act Density 0.024%

    No Known Activations