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

    Neuronpedia

    INDEX
    Explanations

    patterns related to changes and fluctuations in data, specifically focusing on increases and decreases in measurements

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

    Reaching a stable level or plateau

    np_acts-logits-general · gemini-2.0-flash

    reaching a stable state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hadi
    -0.51
    <bos>
    -0.50
    ovec
    -0.49
    httphttps
    -0.47
    anth
    -0.41
    äume
    -0.40
    transformed
    -0.40
    щен
    -0.39
     pilo
    -0.38
     futura
    -0.38
    POSITIVE LOGITS
     plateau
    1.39
     stagn
    1.37
     stagnant
    1.30
     stagnation
    1.29
     stabilize
    1.17
    plateau
    1.16
     stable
    1.12
     stabilized
    1.09
     stabili
    1.09
     stalled
    1.08
    Act Density 0.402%

    No Known Activations