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

    Neuronpedia

    INDEX
    Explanations

    references to "em" throughout the text, indicating a focus on emotional content

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

    words containing em or emulsion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Prato
    -0.56
     intersti
    -0.55
     PeEnEo
    -0.54
    ⋱
    -0.54
    ſicht
    -0.52
    Personensuche
    -0.51
    🛢
    -0.51
     препратки
    -0.51
    Pratique
    -0.50
     Sotto
    -0.50
    POSITIVE LOGITS
    em
    2.50
    EM
    1.63
     em
    1.34
    Em
    1.34
     Em
    1.28
     EM
    1.15
    ems
    1.05
    ém
    0.86
    emes
    0.84
    emm
    0.83
    Act Density 0.008%

    No Known Activations