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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating admissions or confessions

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

    admitted to / confessed to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    because
    -0.41
     extranjera
    -0.39
     bienven
    -0.39
     vectorielles
    -0.38
     Apalagi
    -0.38
     précisément
    -0.37
     capitale
    -0.37
     because
    -0.37
     sprawy
    -0.36
     dépla
    -0.36
    POSITIVE LOGITS
     AssemblyTitle
    0.53
    PropertyGroup
    0.51
    っこう
    0.51
     >=",
    0.50
     <>",
    0.49
    LLocation
    0.49
    toise
    0.48
    inSlope
    0.47
    loit
    0.46
    GEBURTS
    0.45
    Act Density 0.012%

    No Known Activations