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

    Neuronpedia

    INDEX
    Explanations

    references to "phantom" and related concepts in various contexts

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

    phantom behavior/barrier/crossing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Inscrivez
    -0.49
    väg
    -0.46
     guías
    -0.45
    roots
    -0.45
    makeText
    -0.44
     médié
    -0.44
    kách
    -0.43
    Potatoes
    -0.43
    Roots
    -0.43
    角
    -0.42
    POSITIVE LOGITS
     Phantom
    2.41
    Phantom
    2.28
     phantom
    2.28
    phantom
    2.06
    antoms
    1.48
    PHAN
    1.09
    Phan
    1.09
     phan
    0.94
     Phan
    0.93
    phan
    0.87
    Act Density 0.005%

    No Known Activations